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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Co
    -0.07
     Jurassic
    -0.07
    .Grid
    -0.06
    _entries
    -0.06
     folk
    -0.06
    _Tool
    -0.06
     Dock
    -0.06
     °
    -0.06
     الي
    -0.06
     Bands
    -0.06
    POSITIVE LOGITS
     santé
    0.06
    ofilm
    0.06
     Arap
    0.06
    pciones
    0.06
    sizlik
    0.06
    Moment
    0.06
    (tuple
    0.06
    TRGL
    0.06
     Blaze
    0.06
    (hWnd
    0.06
    Act Density 0.014%

    No Known Activations