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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (tokens consisting of digits) in code or text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     территор
    -0.06
    594
    -0.06
    Prostit
    -0.06
    одейств
    -0.06
     abrupt
    -0.06
    _ENSURE
    -0.06
     positioning
    -0.06
     přece
    -0.06
    谱
    -0.06
     terminology
    -0.06
    POSITIVE LOGITS
     SOFTWARE
    0.07
    WHITE
    0.06
    962
    0.06
     Antar
    0.06
     Pilot
    0.06
     लगत
    0.06
    �
    0.06
     Sergey
    0.06
     проведения
    0.06
    ادل
    0.06
    Act Density 0.075%

    No Known Activations