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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _su
    -0.07
    OTOR
    -0.06
     EA
    -0.06
    ození
    -0.06
    에서의
    -0.06
     nudity
    -0.06
    ouve
    -0.06
    apı
    -0.06
     angel
    -0.06
     DatePicker
    -0.06
    POSITIVE LOGITS
    ît
    0.07
     органів
    0.06
    �
    0.06
    ,[
    0.06
     varsa
    0.06
    шев
    0.06
    542
    0.06
     smarty
    0.06
     lâu
    0.06
     правиль
    0.06
    Act Density 0.000%

    No Known Activations