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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مقالات
    -0.07
     gradual
    -0.07
    _documents
    -0.07
    (calc
    -0.07
    .ReadAllText
    -0.06
     consequently
    -0.06
    国民经济
    -0.06
    _:
    -0.06
    _individual
    -0.06
    BUY
    -0.06
    POSITIVE LOGITS
     passing
    0.08
    贴心
    0.07
    special
    0.07
    ꡕ
    0.07
     RAT
    0.07
     callback
    0.07
    无助
    0.07
    spi
    0.06
     Ende
    0.06
    星光
    0.06
    Act Density 0.006%

    No Known Activations