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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron activates on mathematical notation and numbers—i.e. tokens that are part of equations, numeric literals, or formula syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sst
    -0.07
    -$
    -0.06
    stage
    -0.06
    (i
    -0.06
    partners
    -0.06
     General
    -0.06
    field
    -0.06
     host
    -0.06
    -Smith
    -0.06
     undergo
    -0.06
    POSITIVE LOGITS
    (TypeError
    0.08
     trailing
    0.07
    EMPLATE
    0.07
    /ph
    0.06
    .bot
    0.06
    =<?
    0.06
    .DOM
    0.06
    (nome
    0.06
    님
    0.06
    รณ
    0.06
    Act Density 0.011%

    No Known Activations