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

    Neuronpedia

    INDEX
    Explanations

    programming data/properties/ids

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers (variable, function, class, or property names) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    workspace
    -0.07
     unary
    -0.06
    	response
    -0.06
    XX
    -0.06
    Term
    -0.06
    pler
    -0.06
    (hit
    -0.06
     Bay
    -0.06
    ء
    -0.06
    ember
    -0.06
    POSITIVE LOGITS
     ryb
    0.07
     البل
    0.06
    τικ
    0.06
     بنی
    0.06
     بن
    0.06
    iphertext
    0.06
     इतन
    0.06
     Αν
    0.06
    おり
    0.06
     metavar
    0.06
    Act Density 0.067%

    No Known Activations