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

    Neuronpedia

    INDEX
    Explanations

    words related to tension, change, strong emotions, and resolving conflicts

    oai_token-act-pair · gemini-2.0-flash

    State changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -0.38
     topped
    -0.37
     led
    -0.35
    type
    -0.33
    あれば
    -0.33
    нена
    -0.33
    소
    -0.32
     Corintios
    -0.32
    eradish
    -0.31
     completos
    -0.31
    POSITIVE LOGITS
    <bos>
    0.96
    MLLoader
    0.90
    +#+#
    0.87
     &___
    0.85
    TypedDataSet
    0.79
    WireFormatLite
    0.76
    verwijspagina
    0.73
     createState
    0.71
    Jeografia
    0.70
    jspb
    0.69
    Act Density 3.800%

    No Known Activations