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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens, especially floating-point numbers and measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yd
    -0.07
    İZ
    -0.07
    .getData
    -0.06
     заход
    -0.06
    angular
    -0.06
    _started
    -0.06
    .sqlite
    -0.06
    .ToLower
    -0.06
     exceeded
    -0.06
    .yang
    -0.06
    POSITIVE LOGITS
     //!↵
    0.07
    _PR
    0.06
    ORMAT
    0.06
     DisplayName
    0.06
     expression
    0.06
     мы
    0.06
     Paw
    0.06
     IEnumerator
    0.06
     residual
    0.06
     Buying
    0.06
    Act Density 0.180%

    No Known Activations