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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially floating‐point numbers (decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uccess
    -0.06
    imators
    -0.06
    .Link
    -0.06
    validators
    -0.06
     )[
    -0.06
    LayoutConstraint
    -0.06
    ']."
    -0.06
    /chat
    -0.06
    .two
    -0.06
    EQUAL
    -0.06
    POSITIVE LOGITS
    SED
    0.07
    'hui
    0.07
     získat
    0.07
     getResource
    0.06
     gearing
    0.06
    OLID
    0.06
     групи
    0.06
     ná
    0.06
    anchise
    0.06
    	pl
    0.06
    Act Density 0.003%

    No Known Activations