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

    Neuronpedia

    INDEX
    Explanations

    nuclear power, global, bomb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ő
    0.91
    ParameterActive
    0.88
     Некоторые
    0.88
     gördüğünüz
    0.85
     neke
    0.84
     különböző
    0.84
    ő
    0.82
    Packard
    0.81
    പം
    0.80
    ير
    0.80
    POSITIVE LOGITS
    at
    0.80
    al
    0.80
    ans
    0.80
    res
    0.75
    all
    0.72
    and
    0.71
    ри
    0.70
    ac
    0.68
    separ
    0.68
    xk
    0.67
    Act Density 0.000%

    No Known Activations