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

    Neuronpedia

    INDEX
    Explanations

    company name, policies, wide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.92
    க்
    0.83
    мимо
    0.82
     библиоте
    0.80
    лна
    0.80
     conclu
    0.78
    ლის
    0.77
    ف
    0.77
    л
    0.76
    ك
    0.75
    POSITIVE LOGITS
    t
    1.20
    1
    1.04
    g
    1.00
    Company
    0.86
    y
    0.83
    w
    0.82
    wirtschaft
    0.82
    f
    0.77
    A
    0.77
    es
    0.75
    Act Density 0.032%

    No Known Activations