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

    Neuronpedia

    INDEX
    Explanations

    Javascript code syntax.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cí
    -0.46
    ))]
    -0.45
    '];?>
    -0.44
     ketahui
    -0.42
     tre
    -0.42
     tại
    -0.42
     ma
    -0.42
    ilus
    -0.41
     ta
    -0.40
    AutoField
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.89
     raiſ
    0.82
     itſelf
    0.82
     createState
    0.78
    ритори
    0.77
     auffi
    0.77
     myſelf
    0.76
     chofe
    0.75
     juſ
    0.74
     ſtate
    0.73
    Act Density 0.900%

    No Known Activations