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

    Neuronpedia

    INDEX
    Explanations

    programming context examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     routinely
    -0.84
     extraordinary
    -0.84
     showed
    -0.81
    動機
    -0.80
     still
    -0.79
     had
    -0.77
     dumped
    -0.76
     чесно
    -0.75
     extravagant
    -0.75
     schnellen
    -0.74
    POSITIVE LOGITS
     produto
    0.94
    чивать
    0.93
    California
    0.91
     bardzo
    0.91
     conteúdos
    0.91
     Californian
    0.89
     naší
    0.88
    っているので
    0.86
    relle
    0.86
     Produkt
    0.85
    Act Density 0.008%

    No Known Activations