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

    Neuronpedia

    INDEX
    Explanations

    Contrasting adjectives and concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assets
    -0.07
    ]+)/
    -0.07
    (uid
    -0.06
     joker
    -0.06
     yanı
    -0.06
    _community
    -0.06
     terminate
    -0.06
     frank
    -0.06
     کش
    -0.06
    Pref
    -0.06
    POSITIVE LOGITS
    荒
    0.08
     disks
    0.07
    uspendLayout
    0.07
    uibModal
    0.06
    리는
    0.06
    保
    0.06
    串
    0.06
     tackle
    0.06
    uards
    0.06
    │
    0.06
    Act Density 0.002%

    No Known Activations