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

    Neuronpedia

    INDEX
    Explanations

    $x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reverted
    -0.07
     catcher
    -0.07
    cool
    -0.07
    variables
    -0.06
    psi
    -0.06
     обов
    -0.06
     fabs
    -0.06
    Ef
    -0.06
     knitting
    -0.06
     aç
    -0.06
    POSITIVE LOGITS
    �
    0.07
    �
    0.07
    -runtime
    0.07
     عش
    0.07
    _constants
    0.07
    _literals
    0.06
    005
    0.06
    ToShow
    0.06
     labelled
    0.06
    orrow
    0.06
    Act Density 0.003%

    No Known Activations