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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedPtr
    -0.07
     Format
    -0.07
     začala
    -0.06
     Euro
    -0.06
     "//
    -0.06
     bảo
    -0.06
     rodi
    -0.06
     unidad
    -0.06
    alary
    -0.06
    guards
    -0.06
    POSITIVE LOGITS
     Straw
    0.07
    _strcmp
    0.06
    ız
    0.06
    ormap
    0.06
    _ipc
    0.06
    tails
    0.06
    lexport
    0.06
    她们
    0.06
    GridLayout
    0.06
    inous
    0.06
    Act Density 0.002%

    No Known Activations