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

    Neuronpedia

    INDEX
    Explanations

    two pounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countenance
    0.44
    ativas
    0.43
     worsen
    0.43
    ਨ
    0.42
     gekennzeichnet
    0.41
    sides
    0.40
     indelible
    0.40
     FORE
    0.40
     nostrils
    0.38
     unsettled
    0.38
    POSITIVE LOGITS
    with
    0.44
    initConfig
    0.42
     múltiplos
    0.42
     mixto
    0.41
     heater
    0.39
     guer
    0.39
     miếng
    0.39
     hỏi
    0.38
     店
    0.38
     arti
    0.38
    Act Density 0.000%

    No Known Activations