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

    Neuronpedia

    INDEX
    Explanations

    allure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ти
    0.74
    מד
    0.67
    മ
    0.66
    ны
    0.66
    ّم
    0.66
    мо
    0.64
    ان
    0.63
     to
    0.63
    מ
    0.63
    ва
    0.62
    POSITIVE LOGITS
    of
    0.70
     INTEGR
    0.59
    </strong>
    0.57
     Tennyson
    0.55
     cù
    0.54
     contribut
    0.53
     solicitors
    0.52
    :
    0.52
    orian
    0.52
     eficacia
    0.52
    Act Density 0.000%

    No Known Activations