Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or ethical approval and consent in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Consent/approval/permission obtained or received

    np_acts-logits-general · gemini-2.0-flash

    consent obtained was received

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.91
    rungsseite
    -0.88
     فريبيس
    -0.87
     utafitiHapana
    -0.86
     BrowserModule
    -0.86
    mergeFrom
    -0.83
    ISupport
    -0.81
    UnsafeEnabled
    -0.81
    WithIOException
    -0.79
    ImageContext
    -0.78
    POSITIVE LOGITS
     also
    0.42
    ास्त
    0.41
     Communications
    0.41
     communications
    0.40
     advanced
    0.40
     durs
    0.40
    advanced
    0.40
     Communication
    0.39
    detal
    0.39
    Cabe
    0.39
    Act Density 0.304%

    No Known Activations