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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     U
    -0.08
     <$
    -0.07
    >\<
    -0.07
    _payload
    -0.07
    athlon
    -0.06
    لا
    -0.06
     coating
    -0.06
    {{$
    -0.06
    <P
    -0.06
    resolved
    -0.06
    POSITIVE LOGITS
     elites
    0.07
     está
    0.07
    IMENT
    0.07
    電子郵件
    0.07
    痫
    0.06
    drv
    0.06
    因子
    0.06
    华丽
    0.06
    הלך
    0.06
    乐器
    0.06
    Act Density 0.002%

    No Known Activations