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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decad
    -0.07
    퀘
    -0.07
    shop
    -0.07
    calc
    -0.07
    _METADATA
    -0.07
    _FACTOR
    -0.07
    鼹
    -0.07
     Deferred
    -0.06
    имер
    -0.06
    abilia
    -0.06
    POSITIVE LOGITS
    סות
    0.08
    .native
    0.07
     Sing
    0.07
    同
    0.07
    红旗
    0.07
    .os
    0.07
    Av
    0.06
    𬴊
    0.06
    _PUT
    0.06
    任
    0.06
    Act Density 0.021%

    No Known Activations