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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :".
    -0.08
    志愿者
    -0.07
    弘扬
    -0.07
     אזרחי
    -0.07
    彰
    -0.07
    ����
    -0.07
     profiling
    -0.07
     fark
    -0.07
     forwards
    -0.07
     kitchens
    -0.07
    POSITIVE LOGITS
    us
    0.13
    icus
    0.09
    inus
    0.08
    ﾑ
    0.07
    _pal
    0.07
     Bu
    0.07
    どんな
    0.07
     multiplier
    0.07
    pus
    0.07
    Metal
    0.07
    Act Density 0.060%

    No Known Activations