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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Writes
    -0.07
    _corr
    -0.07
    /cs
    -0.07
     bladder
    -0.06
    Fast
    -0.06
     Arr
    -0.06
    usercontent
    -0.06
    LF
    -0.06
     Question
    -0.06
    宋体
    -0.06
    POSITIVE LOGITS
     accountId
    0.07
    dí
    0.07
    aa
    0.07
    dzą
    0.07
    잃
    0.07
    idepress
    0.07
    랙
    0.07
     أقل
    0.06
     ids
    0.06
    eday
    0.06
    Act Density 0.013%

    No Known Activations