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

    Neuronpedia

    INDEX
    Explanations

    missing kids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    talking
    0.88
    Ac
    0.80
    Bers
    0.78
    Veronica
    0.77
    UNC
    0.75
    ম
    0.72
    camore
    0.71
    Bare
    0.71
    S
    0.71
    Faction
    0.71
    POSITIVE LOGITS
    形式
    0.79
     resembled
    0.79
     Maruti
    0.77
     Zn
    0.77
    மர்
    0.77
     honda
    0.74
    د
    0.74
     hệ
    0.73
     Croydon
    0.73
     Variation
    0.72
    Act Density 0.003%

    No Known Activations