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

    Neuronpedia

    INDEX
    Explanations

    lists, definitions, guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៥
    0.67
    ൮
    0.64
    zechoslovakia
    0.63
    yección
    0.62
     πε
    0.61
    wała
    0.61
     putern
    0.60
    itespace
    0.59
    ੰਜ
    0.59
     ৭
    0.59
    POSITIVE LOGITS
    ل
    0.84
    ის
    0.83
     in
    0.79
    ing
    0.76
     insur
    0.76
    માં
    0.74
    ת
    0.69
     can
    0.68
    ח
    0.68
    ק
    0.68
    Act Density 0.693%

    No Known Activations