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

    Neuronpedia

    INDEX
    Explanations

    6 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昵
    -0.07
    alm
    -0.07
    (preg
    -0.07
    Ȩ
    -0.07
    陆
    -0.07
    -low
    -0.06
    纯净
    -0.06
    盗
    -0.06
    SEQ
    -0.06
    Cumhurba
    -0.06
    POSITIVE LOGITS
    Ꙭ
    0.07
    .GetCurrentMethod
    0.07
    .Cos
    0.07
    :"-"`↵
    0.07
    报社
    0.07
     cancellation
    0.07
     harassment
    0.06
    ⊋
    0.06
    -INFRINGEMENT
    0.06
     courage
    0.06
    Act Density 0.005%

    No Known Activations