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

    Neuronpedia

    INDEX
    Explanations

    structured text enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspekt
    0.46
     konflikt
    0.46
     agres
    0.46
     konfl
    0.45
     subjekt
    0.45
     alumnos
    0.44
     algorit
    0.43
    異なる
    0.42
     conflic
    0.41
    ਼
    0.41
    POSITIVE LOGITS
    ње
    0.53
     снять
    0.48
    Ну
    0.48
     أو
    0.48
     на
    0.47
    ?>
    0.46
     anytime
    0.46
    ków
    0.46
     ,
    0.46
     żeby
    0.46
    Act Density 0.009%

    No Known Activations