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

    Neuronpedia

    INDEX
    Explanations

    credit scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excell
    -0.08
    专题
    -0.08
     suck
    -0.06
     provoked
    -0.06
    apos
    -0.06
     sách
    -0.06
    itating
    -0.06
    略
    -0.06
    三个月
    -0.06
    ,s
    -0.06
    POSITIVE LOGITS
    ชาย
    0.07
    ErrMsg
    0.07
    كيف
    0.07
     innov
    0.07
    |"
    0.07
     #'
    0.07
    ":"/
    0.07
     METHOD
    0.07
    >H
    0.07
    setUp
    0.06
    Act Density 0.010%

    No Known Activations