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

    Neuronpedia

    INDEX
    Explanations

    consensus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赠
    -0.08
    anie
    -0.07
     Kane
    -0.07
    tid
    -0.07
    袭
    -0.07
    סו
    -0.06
    iała
    -0.06
    mmo
    -0.06
     מסו
    -0.06
    כל
    -0.06
    POSITIVE LOGITS
    딮
    0.07
     salari
    0.07
     Ком
    0.07
     USING
    0.06
    产业化
    0.06
     Agricult
    0.06
    ,arg
    0.06
    formatted
    0.06
    流れ
    0.06
     cudaMemcpy
    0.06
    Act Density 0.017%

    No Known Activations