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

    Neuronpedia

    INDEX
    Explanations

    code with variable values

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers—variable names in programming snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Suns
    -0.07
    actions
    -0.06
    redicate
    -0.06
     BRA
    -0.06
    ovolta
    -0.06
     가입
    -0.06
    _hits
    -0.06
    -common
    -0.06
     Widgets
    -0.06
    exampleInput
    -0.06
    POSITIVE LOGITS
     jusqu
    0.07
     migrating
    0.07
     esposa
    0.07
     восстанов
    0.06
     prox
    0.06
     culmination
    0.06
     třet
    0.06
     kat
    0.06
     aliqu
    0.06
    	parser
    0.06
    Act Density 0.090%

    No Known Activations