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

    Neuronpedia

    INDEX
    Explanations

    approximation

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of mathematical approximations or parameter‐estimation terms (e.g. “approximation,” numerical coefficients, and related technical modifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    len
    -0.07
     dokon
    -0.07
     hỗn
    -0.06
     outreach
    -0.06
     Fan
    -0.06
     Henrik
    -0.06
     зі
    -0.06
    .ButterKnife
    -0.06
     SimpleName
    -0.05
    Ix
    -0.05
    POSITIVE LOGITS
     disappointment
    0.07
    Launching
    0.07
     Choices
    0.07
    rule
    0.07
    过来
    0.07
     Tribunal
    0.07
     GMC
    0.06
     DECLARE
    0.06
    .escape
    0.06
     akıl
    0.06
    Act Density 0.009%

    No Known Activations