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

    Neuronpedia

    INDEX
    Explanations

    espanol ¡Claro! / ¡Sí!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nd
    2.27
    ndan
    2.05
    ди
    2.02
     argv
    1.99
    d
    1.99
     PartialEq
    1.98
    dato
    1.94
    eee
    1.92
     comenz
    1.88
    тке
    1.87
    POSITIVE LOGITS
    ה
    1.90
    credibly
    1.84
    యన్
    1.82
    増加
    1.77
    }//
    1.74
     взгляд
    1.72
     væ
    1.72
    }{
    1.71
     கூடிய
    1.71
    }{$
    1.69
    Act Density 0.002%

    No Known Activations