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

    Neuronpedia

    INDEX
    Explanations

    connecting words

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing floating‐point numbers (decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    巡
    -0.07
    Wilson
    -0.06
    erver
    -0.06
     Wilson
    -0.06
    ือก
    -0.06
    _dll
    -0.06
    removed
    -0.06
    (cn
    -0.06
     ض
    -0.06
    ух
    -0.06
    POSITIVE LOGITS
    τικά
    0.07
     UNIQUE
    0.07
     Searching
    0.07
    	DWORD
    0.07
     Weed
    0.07
     новых
    0.06
    ahkan
    0.06
     genuinely
    0.06
     posY
    0.06
    INES
    0.06
    Act Density 0.064%

    No Known Activations