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

    Neuronpedia

    INDEX
    Explanations

    however, but, estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funcionários
    0.49
    殭
    0.48
    😱
    0.47
    ورة
    0.47
    小說
    0.47
    ಗಳು
    0.46
     immig
    0.45
     Vold
    0.45
     installieren
    0.45
    ،
    0.45
    POSITIVE LOGITS
    हमें
    0.49
     abbiamo
    0.44
     нам
    0.42
     pembelian
    0.42
     fruitless
    0.40
     we
    0.39
     Tribe
    0.39
    我们
    0.38
    इसमें
    0.38
     contribution
    0.38
    Act Density 0.003%

    No Known Activations