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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     رح
    -0.07
     ऑफ
    -0.07
    ómo
    -0.07
    USH
    -0.07
     desea
    -0.07
    ><![
    -0.07
    ICA
    -0.07
     del
    -0.07
     Fel
    -0.07
    uerdo
    -0.06
    POSITIVE LOGITS
     bmi
    0.06
     ◆
    0.06
    "=>"
    0.06
    .FullName
    0.06
    医学
    0.06
    予
    0.06
     rnd
    0.06
    _offer
    0.06
    Roles
    0.06
    0.06
    Act Density 0.036%

    No Known Activations