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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ábado
    -0.08
    ฯ
    -0.07
    )}>↵
    -0.07
     Decimal
    -0.07
    }}"
    -0.07
     storia
    -0.07
    "`
    -0.07
    leet
    -0.07
    LECT
    -0.07
    kın
    -0.07
    POSITIVE LOGITS
     Welsh
    0.06
     gift
    0.06
    Datas
    0.06
     consult
    0.06
    (datas
    0.06
    By
    0.06
    263
    0.06
     fluffy
    0.06
    _prog
    0.06
     облад
    0.06
    Act Density 0.002%

    No Known Activations