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

    Neuronpedia

    INDEX
    Explanations

    dish soap, law, nails, yellow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    0.96
    न
    0.86
    ier
    0.85
     einen
    0.84
     свою
    0.84
    et
    0.84
    ower
    0.83
    an
    0.81
    ok
    0.81
     personnalisé
    0.81
    POSITIVE LOGITS
     ώστε
    0.87
    sufficiency
    0.86
     mediast
    0.83
    ны
    0.82
    SignUp
    0.82
    ログ
    0.81
    >):
    0.80
     freg
    0.80
    Corre
    0.79
    Khokhlov
    0.79
    Act Density 0.002%

    No Known Activations