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

    Neuronpedia

    INDEX
    Explanations

    species descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frail
    -0.08
    _BLOCK
    -0.07
    얀
    -0.07
    ercicio
    -0.07
    朸
    -0.07
    鲡
    -0.07
    FY
    -0.06
    罢
    -0.06
     WRITE
    -0.06
    خيل
    -0.06
    POSITIVE LOGITS
     Penny
    0.07
     Motion
    0.07
    .With
    0.07
    犯罪
    0.06
    덖
    0.06
    一度
    0.06
    =no
    0.06
    生態
    0.06
     Downtown
    0.06
    Programming
    0.06
    Act Density 0.004%

    No Known Activations