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

    Neuronpedia

    INDEX
    Explanations

    Technical/Informational texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DATABASE
    -0.08
     Pierre
    -0.07
    \Migration
    -0.07
    .extra
    -0.07
    Arn
    -0.07
    .sponge
    -0.07
     Bieber
    -0.07
    ULSE
    -0.07
    mittel
    -0.07
     Tiên
    -0.07
    POSITIVE LOGITS
     move
    0.07
    ;]/
    0.07
    ）↵
    0.07
    上班
    0.06
    ++){↵↵
    0.06
    葬
    0.06
    瑶
    0.06
     vd
    0.06
    ⾛
    0.06
     Mayweather
    0.06
    Act Density 0.000%

    No Known Activations