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

    Neuronpedia

    INDEX
    Explanations

    following instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wobei
    0.46
    dyž
    0.42
     dimensioni
    0.42
     برطانیہ
    0.42
     elektrische
    0.42
    沃尔
    0.41
     plabic
    0.41
     fiabilité
    0.41
     کیا۔
    0.40
     ذریع
    0.40
    POSITIVE LOGITS
    ut
    0.41
    ari
    0.38
    ates
    0.37
    "})
    0.37
    mp
    0.37
    不要
    0.36
    ate
    0.36
    fledged
    0.36
    ors
    0.35
    atos
    0.35
    Act Density 0.001%

    No Known Activations