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

    Neuronpedia

    INDEX
    Explanations

    human experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     معنی
    -0.07
     alles
    -0.07
     sobre
    -0.07
     serge
    -0.06
    /pdf
    -0.06
     ему
    -0.06
    one
    -0.06
    로나
    -0.06
     newer
    -0.06
    -speaking
    -0.06
    POSITIVE LOGITS
    illet
    0.08
     βά
    0.07
    HeadersHeightSizeMode
    0.06
     お
    0.06
    _cover
    0.06
    >(),
    0.06
    .original
    0.05
    ============↵
    0.05
    貸
    0.05
     Bảo
    0.05
    Act Density 0.477%

    No Known Activations