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

    Neuronpedia

    INDEX
    Explanations

    became

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ьаж
    -0.63
     GetEnumerator
    -0.59
    __*/
    -0.58
     indisponible
    -0.58
     nearer
    -0.58
     hostage
    -0.56
    PhysRevD
    -0.56
     Sutra
    -0.55
     Assim
    -0.54
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
    例文帳に追加
    0.50
     بيها
    0.50
     &
    0.49
    InstrumentedTest
    0.49
    ыгана
    0.49
    findpost
    0.48
    发表于
    0.47
     burada
    0.47
    脚注の使い方
    0.46
     helyez
    0.45
    Act Density 0.004%

    No Known Activations