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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (e.g. line numbers, indices, or other standalone digits) in code and error traces.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hund
    -0.07
    _existing
    -0.06
     whitespace
    -0.06
     soothing
    -0.06
    .scroll
    -0.06
     coined
    -0.06
    related
    -0.06
     nurturing
    -0.06
     nurture
    -0.06
    .department
    -0.06
    POSITIVE LOGITS
     aster
    0.07
     AVR
    0.07
     Carnival
    0.07
    msgid
    0.06
     simul
    0.06
     طبق
    0.06
     triang
    0.06
    	cp
    0.06
    (OP
    0.06
    (cfg
    0.06
    Act Density 0.003%

    No Known Activations