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

    Neuronpedia

    INDEX
    Explanations

    responsibility taken for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IDE
    0.48
    et
    0.47
    ige
    0.47
     in
    0.47
    ite
    0.46
    aben
    0.46
    ći
    0.43
    te
    0.42
    ile
    0.42
    Billing
    0.42
    POSITIVE LOGITS
     evanes
    0.53
     floc
    0.50
     यूपी
    0.49
    фри
    0.49
    \%.
    0.49
     entstehen
    0.48
    ه
    0.47
    ܬ
    0.47
    هرب
    0.47
     Giuliani
    0.47
    Act Density 0.002%

    No Known Activations