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

    Neuronpedia

    INDEX
    Explanations

    normalization and direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ak
    -0.07
    _keys
    -0.07
    clid
    -0.07
    LOOD
    -0.07
    OUND
    -0.07
    ]-
    -0.06
    рид
    -0.06
     Een
    -0.06
    aris
    -0.06
     Wert
    -0.06
    POSITIVE LOGITS
    _WRONLY
    0.07
    _media
    0.06
    	MPI
    0.06
    [strlen
    0.06
     ctypes
    0.06
     nepř
    0.06
     บ
    0.05
    _KEYBOARD
    0.05
    .printStackTrace
    0.05
    靠
    0.05
    Act Density 0.014%

    No Known Activations