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

    Neuronpedia

    INDEX
    Explanations

    slower than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supercritical
    1.02
     CarPlay
    0.92
     Rosso
    0.91
     BRA
    0.90
     Zag
    0.90
    successor
    0.89
     Freeway
    0.88
    Smart
    0.86
     Hesse
    0.85
    global
    0.85
    POSITIVE LOGITS
     Myl
    1.03
     wardrobes
    0.97
    iment
    0.95
     palettes
    0.94
    覃
    0.92
    вор
    0.91
    IMENT
    0.91
    cmt
    0.90
     Yn
    0.89
    馆
    0.88
    Act Density 0.467%

    No Known Activations