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

    Neuronpedia

    INDEX
    Explanations

    make sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automóvil
    0.49
    कडील
    0.46
    十足
    0.46
    inskii
    0.45
    ❣
    0.44
     ruh
    0.42
     externes
    0.42
     akar
    0.42
    nek
    0.41
    的高
    0.41
    POSITIVE LOGITS
    ್ರೆ
    0.52
     ট্যাবলেট
    0.48
     வாழை
    0.46
    િ
    0.46
    െ
    0.45
    urno
    0.45
     personalization
    0.43
     personalisation
    0.43
    正しい
    0.42
     சுண்ணா
    0.42
    Act Density 0.002%

    No Known Activations