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

    Neuronpedia

    INDEX
    Explanations

    Legal and scientific documents

    np_max-act · gemini-2.0-flash

    This neuron primarily detects numeric tokens and number-like sequences (e.g., years, identification numbers, grant or code numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Targets
    -0.07
    	TR
    -0.07
     SKIP
    -0.06
     Flesh
    -0.06
    (prefix
    -0.06
    -linear
    -0.06
     fungus
    -0.06
    KNOWN
    -0.06
     reject
    -0.06
     bend
    -0.06
    POSITIVE LOGITS
     للم
    0.07
     />}↵
    0.07
     giản
    0.06
     لد
    0.06
     المص
    0.06
    /npm
    0.06
    Об
    0.06
    كيب
    0.06
     높은
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations