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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enarios
    -0.07
     pistols
    -0.07
    anggal
    -0.06
    िसक
    -0.06
    による
    -0.06
     aws
    -0.06
    ders
    -0.06
    가격
    -0.06
    海道
    -0.06
    _indent
    -0.06
    POSITIVE LOGITS
    ?>↵↵
    0.07
     Guinness
    0.07
    Text
    0.07
    ุส
    0.07
    +↵
    0.07
    wang
    0.07
    double
    0.07
     continuation
    0.06
    -the
    0.06
     ignore
    0.06
    Act Density 0.025%

    No Known Activations