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

    Neuronpedia

    INDEX
    Explanations

    Application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }),↵↵
    -0.06
    />.↵
    -0.06
    <(
    -0.06
     Sparks
    -0.06
    عداد
    -0.06
     cylinder
    -0.06
     pageNum
    -0.06
     Tobacco
    -0.06
    śli
    -0.05
    Destroy
    -0.05
    POSITIVE LOGITS
    руг
    0.07
    instrument
    0.06
    _Rem
    0.06
    yyyyMMdd
    0.06
    (cfg
    0.06
    baş
    0.06
     Lace
    0.06
     divul
    0.06
    epoch
    0.06
    aceous
    0.06
    Act Density 0.045%

    No Known Activations