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

    Neuronpedia

    INDEX
    Explanations

    say "1"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /false
    -0.08
    半
    -0.07
    设立了
    -0.07
     sổ
    -0.07
     nửa
    -0.07
    multiply
    -0.07
     אחרים
    -0.07
    .mov
    -0.06
    .single
    -0.06
    ᠰ
    -0.06
    POSITIVE LOGITS
    .permission
    0.08
    onte
    0.07
    Unix
    0.07
    ]]↵
    0.07
     telling
    0.07
    (sec
    0.07
     remembered
    0.07
    //---------------------------------------------------------------------------↵
    0.06
    ывать
    0.06
    "};↵↵
    0.06
    Act Density 0.002%

    No Known Activations