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

    Neuronpedia

    INDEX
    Explanations

    financial statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limiting
    0.48
     flared
    0.47
     Zn
    0.45
     maksimal
    0.43
     variational
    0.43
     leit
    0.43
     categorization
    0.43
     decals
    0.42
     Flare
    0.42
     Zulu
    0.41
    POSITIVE LOGITS
    d
    0.52
    AFTER
    0.48
    游泳
    0.47
    ACTER
    0.46
    FORMANCE
    0.45
    a
    0.45
    TIC
    0.44
    l
    0.44
     phénom
    0.43
    Understand
    0.42
    Act Density 0.003%

    No Known Activations