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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yol
    -0.07
    源
    -0.05
    Flo
    -0.05
     ổn
    -0.05
     dispositivo
    -0.05
     bordel
    -0.05
    .syntax
    -0.05
     psychiat
    -0.05
     beden
    -0.05
     Elm
    -0.05
    POSITIVE LOGITS
    XX
    0.07
     Taxes
    0.07
     malaria
    0.07
    .event
    0.07
     سیستم
    0.07
    _TestCase
    0.06
    จากการ
    0.06
    _power
    0.06
    stone
    0.06
     color
    0.06
    Act Density 0.014%

    No Known Activations