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

    Neuronpedia

    INDEX
    Explanations

    programming code method call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܂
    0.45
     جنہوں
    0.43
    pid
    0.43
    ethylsulfanyl
    0.41
    velden
    0.40
    isph
    0.40
    hurt
    0.40
    رم
    0.40
    gne
    0.40
    glomer
    0.39
    POSITIVE LOGITS
    关键字
    0.40
     واذا
    0.39
     如果
    0.38
     关闭
    0.38
     断
    0.37
     一
    0.37
    యర్
    0.37
     discontinuities
    0.36
     још
    0.36
     pomocí
    0.36
    Act Density 0.003%

    No Known Activations