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

    Neuronpedia

    INDEX
    Explanations

    experimental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WillAppear
    -0.63
    }{*}{
    -0.55
     banques
    -0.48
    roppo
    -0.47
    fromCharCode
    -0.46
    aarrggbb
    -0.46
    __.__
    -0.45
     definiert
    -0.45
    <?
    -0.45
     gezet
    -0.45
    POSITIVE LOGITS
     chi̍t
    0.59
     long
    0.57
     forms
    0.54
    enschappelijke
    0.54
     spirit
    0.54
    原始内容存档于
    0.54
    ochemistry
    0.53
    KommentareTeilen
    0.51
    MigrationBuilder
    0.51
    ism
    0.50
    Act Density 0.005%

    No Known Activations