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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (toolbar
    -0.08
    getText
    -0.08
    metadata
    -0.07
    .Comp
    -0.07
     recruiters
    -0.07
    aur
    -0.07
    _cuda
    -0.06
    .Web
    -0.06
     MULT
    -0.06
    .getStringExtra
    -0.06
    POSITIVE LOGITS
    Numero
    0.06
     مرحله
    0.06
     ประก
    0.06
    ecure
    0.05
    imate
    0.05
     violates
    0.05
    力量
    0.05
    人们
    0.05
    _remain
    0.05
    东省
    0.05
    Act Density 0.070%

    No Known Activations