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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to comma tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bigint
    -0.06
    ANI
    -0.06
    	bl
    -0.06
    áč
    -0.06
    -program
    -0.06
    emale
    -0.06
    .instructions
    -0.06
    (session
    -0.06
     widow
    -0.06
    -fr
    -0.06
    POSITIVE LOGITS
     impulses
    0.07
     impressed
    0.07
     vielen
    0.06
     يس
    0.06
     Orden
    0.06
     tossed
    0.06
     barric
    0.06
    -General
    0.06
    SCII
    0.06
    оит
    0.06
    Act Density 0.229%

    No Known Activations