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

    Neuronpedia

    INDEX
    Explanations

    tough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    83
    -0.07
    阳
    -0.07
     почина
    -0.06
     encuent
    -0.06
     Rwanda
    -0.06
    _mA
    -0.06
     혼
    -0.06
    cai
    -0.06
    axter
    -0.06
     userAgent
    -0.06
    POSITIVE LOGITS
     hardness
    0.07
    程
    0.06
    _DEF
    0.06
    殖
    0.06
    Edition
    0.06
     exposures
    0.06
    xxx
    0.06
     Adapter
    0.06
    .OUT
    0.06
     Angebot
    0.06
    Act Density 0.018%

    No Known Activations