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

    Neuronpedia

    INDEX
    Explanations

    don’

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.37
    an
    1.29
    ת
    1.18
    i
    1.13
    at
    1.13
    л
    1.07
    ה
    1.04
    quela
    1.02
    es
    0.94
    in
    0.88
    POSITIVE LOGITS
    tenance
    0.98
    های
    0.94
    ować
    0.93
    nya
    0.92
    layered
    0.90
    ные
    0.89
    ০০
    0.88
    ப்
    0.86
     greats
    0.85
    ному
    0.85
    Act Density 0.063%

    No Known Activations