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

    Neuronpedia

    INDEX
    Explanations

    perfectly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eint
    0.46
     ಯು
    0.42
     النقطه
    0.42
     eigenvalue
    0.39
     Punkt
    0.39
     Göttingen
    0.39
    が増
    0.38
     نقطه
    0.38
    Ζ
    0.38
    点は
    0.38
    POSITIVE LOGITS
    ěné
    0.46
    🇸
    0.40
     선생님
    0.39
     harb
    0.38
     constituency
    0.37
    ເຈ
    0.37
    Qualifier
    0.37
    Rogers
    0.37
    Collider
    0.37
     беру
    0.37
    Act Density 0.000%

    No Known Activations