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

    Neuronpedia

    INDEX
    Explanations

    recent controversies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUS
    0.46
     computed
    0.42
    OPHY
    0.39
     preprocess
    0.39
     PA
    0.38
    饯
    0.38
     PIC
    0.37
     modulo
    0.37
     ಉತ್ತಮ
    0.36
    ЛИ
    0.36
    POSITIVE LOGITS
     controversies
    1.16
     controversy
    1.06
     controvers
    1.04
     controversial
    1.01
     scandals
    1.00
     recente
    0.97
     recentemente
    0.97
     récente
    0.95
     polémica
    0.95
     recientes
    0.94
    Act Density 0.081%

    No Known Activations