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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement, affirmation, or acknowledgement

    oai_token-act-pair · gemini-2.0-flash

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.74
     becauſe
    -0.69
    Personensuche
    -0.66
     fathoms
    -0.60
    SequentialGroup
    -0.59
     itſelf
    -0.58
     Transvaal
    -0.57
    dération
    -0.57
     Danzig
    -0.56
     suns
    -0.56
    POSITIVE LOGITS
    rungsseite
    0.74
    XmlAccessType
    0.62
    sizeCache
    0.52
    bitField
    0.49
     etter
    0.47
    UNGE
    0.46
    readValue
    0.46
     समीक्षक
    0.45
    addPreferredGap
    0.45
    ValueGeneration
    0.45
    Act Density 0.722%

    No Known Activations