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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зывают
    0.77
    ՝
    0.77
     म्हणतात
    0.75
    Bibli
    0.71
    َّة
    0.71
    ಿಕೊಂಡ
    0.71
    надцати
    0.68
     zahrani
    0.68
    FFECT
    0.67
    hões
    0.67
    POSITIVE LOGITS
    Also
    0.89
     other
    0.84
     formatting
    0.81
     statistically
    0.80
     continue
    0.80
     Also
    0.79
     If
    0.79
    If
    0.78
     verify
    0.78
    Each
    0.77
    Act Density 0.039%

    No Known Activations