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

    Neuronpedia

    INDEX
    Explanations

    methods and principles acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    やや
    0.42
    उँ
    0.42
     SB
    0.42
     प्रोत्साहित
    0.42
    бычно
    0.41
     HTTPS
    0.41
     fateful
    0.40
     distinguishing
    0.40
     Mã
    0.40
     indign
    0.39
    POSITIVE LOGITS
    ER
    0.66
     acronym
    0.63
    INA
    0.59
    COM
    0.56
    nungen
    0.53
    INGTON
    0.52
    LES
    0.50
    CAM
    0.49
    2
    0.48
    KAN
    0.48
    Act Density 0.034%

    No Known Activations