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

    Neuronpedia

    INDEX
    Explanations

    yes, bard, interrupted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     તમામ
    0.46
     الجديدة
    0.42
     Dispersion
    0.41
     નવા
    0.40
     exigences
    0.39
    Política
    0.39
     সামগ্র
    0.38
     सभी
    0.38
     Besitz
    0.37
     fullName
    0.37
    POSITIVE LOGITS
    /
    0.51
    /(
    0.43
    rsi
    0.41
    ?
    0.40
    ('
    0.38
     berg
    0.38
    t
    0.38
     ?
    0.37
    mà
    0.36
     nears
    0.36
    Act Density 0.001%

    No Known Activations