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

    Neuronpedia

    INDEX
    Explanations

    perhaps focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    égard
    1.03
     thể
    0.99
    mitting
    0.90
    asság
    0.86
     féidir
    0.85
     whiche
    0.85
     varie
    0.84
    getName
    0.84
    Droite
    0.83
    vì
    0.83
    POSITIVE LOGITS
    izzazione
    0.88
    сто
    0.86
     deltaTime
    0.83
     bibliography
    0.78
    ん
    0.76
     તો
    0.76
    اد
    0.76
    catalyzed
    0.75
    ACLE
    0.74
    atorios
    0.73
    Act Density 0.022%

    No Known Activations