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

    Neuronpedia

    INDEX
    Explanations

    Here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    operatorname
    0.69
    ٔ
    0.68
     jî
    0.68
     --
    0.67
     của
    0.66
     zaś
    0.62
     ـ
    0.62
     кантип
    0.61
    ⅾ
    0.61
    :~
    0.60
    POSITIVE LOGITS
     Here
    1.66
    Here
    1.56
     here
    1.49
    以下の
    1.35
     Despite
    1.25
     这里
    1.23
     এখানে
    1.23
     Following
    1.22
     There
    1.19
    Despite
    1.19
    Act Density 0.415%

    No Known Activations