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

    Neuronpedia

    INDEX
    Explanations

    github repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    셌
    -0.07
    esters
    -0.07
    ej
    -0.06
    DEV
    -0.06
    трат
    -0.06
    返回
    -0.06
     Watts
    -0.06
    CAC
    -0.06
     sensitivity
    -0.06
     CREATE
    -0.06
    POSITIVE LOGITS
    _Link
    0.08
    散布
    0.07
     mosques
    0.07
    𝖎
    0.07
    .menu
    0.07
    完整的
    0.07
    国会
    0.07
    .enumer
    0.07
    //----------------------------------------------------------------------------↵
    0.07
    _bh
    0.07
    Act Density 0.026%

    No Known Activations