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

    Neuronpedia

    INDEX
    Explanations

    phrases related to composition or structure

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

    Something being composed or dependent on something else

    np_acts-logits-general · gemini-2.0-flash

    causal or compositional relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.84
     مشين
    -0.81
    withIdentifier
    -0.78
    RegistryLite
    -0.76
     дописавши
    -0.76
     transfieras
    -0.75
    enderror
    -0.74
     surla
    -0.72
    HasIndex
    -0.71
     INTERESAR
    -0.71
    POSITIVE LOGITS
     primarily
    1.53
     mainly
    1.50
     mostly
    1.48
     largely
    1.47
     entirely
    1.32
     predominantly
    1.29
     chiefly
    1.25
     principally
    1.24
     solely
    1.20
    primarily
    1.16
    Act Density 0.470%

    No Known Activations