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

    Neuronpedia

    INDEX
    Explanations

    directions or methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     codzien
    0.46
     sahiptir
    0.45
    装饰
    0.45
     odborn
    0.45
     tormented
    0.44
    oterapia
    0.44
    அல்ல
    0.44
    你有
    0.44
    otherapie
    0.44
     procédures
    0.43
    POSITIVE LOGITS
     positives
    0.43
    廻
    0.43
    候補
    0.42
     Govt
    0.42
     slip
    0.41
    組
    0.41
    ーム
    0.40
     brewing
    0.40
    測
    0.39
     recession
    0.39
    Act Density 0.008%

    No Known Activations