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

    Neuronpedia

    INDEX
    Explanations

    Sulla's Intervention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.63
    õe
    0.59
     Counties
    0.58
    ریٹر
    0.58
     Kuna
    0.57
     Diario
    0.57
     tượng
    0.57
    igura
    0.55
    㞰
    0.55
     Yara
    0.55
    POSITIVE LOGITS
    kv
    0.57
    を使って
    0.55
    лек
    0.55
    вы
    0.51
    pros
    0.51
    sendKeys
    0.51
     unexpectedly
    0.50
    *
    0.50
     like
    0.49
    netic
    0.49
    Act Density 0.001%

    No Known Activations