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

    Neuronpedia

    INDEX
    Explanations

    code and writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شمال
    -0.07
     Zelda
    -0.07
     purchasers
    -0.07
    销售
    -0.07
     invading
    -0.06
     Accountability
    -0.06
    -bed
    -0.06
     Frid
    -0.06
     increased
    -0.06
     squadron
    -0.06
    POSITIVE LOGITS
    иму
    0.07
     vrai
    0.07
    {:
    0.07
    igion
    0.07
    _UTILS
    0.07
    ラック
    0.07
    IVING
    0.06
    all
    0.06
    ège
    0.06
    rtc
    0.06
    Act Density 0.001%

    No Known Activations