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

    Neuronpedia

    INDEX
    Explanations

    -type

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numbers (decimal numeric values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    HS
    -0.06
    activation
    -0.06
     kuru
    -0.06
    _big
    -0.06
    Annotations
    -0.06
    DS
    -0.06
    _shop
    -0.06
    _store
    -0.06
     Hindu
    -0.06
    _Build
    -0.06
    POSITIVE LOGITS
    Ruby
    0.07
    万元
    0.06
    	parser
    0.06
     Recap
    0.06
    按
    0.06
    Γ
    0.06
    ματα
    0.06
     pursuing
    0.06
     minimise
    0.06
    Phill
    0.06
    Act Density 0.001%

    No Known Activations