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

    Neuronpedia

    INDEX
    Explanations

    green

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of primary color components or channels (like red, green, blue) and their associated values in display or image contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _INV
    -0.06
     tonumber
    -0.05
    	if
    -0.05
    bold
    -0.05
     reinc
    -0.05
    operators
    -0.05
    Volume
    -0.05
     journeys
    -0.05
    ensemble
    -0.05
    outines
    -0.05
    POSITIVE LOGITS
    Getting
    0.07
     grazing
    0.07
    (distance
    0.07
     sporting
    0.07
    (Activity
    0.07
    mn
    0.07
    MakeRange
    0.07
    сім
    0.07
     gider
    0.06
    χεία
    0.06
    Act Density 0.004%

    No Known Activations