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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    JavaScript function definitions and their structures, specifically within module exports.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is picking up on numeric literals with decimal points—that is, floating‐point number tokens in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     predatory
    -0.07
    /v
    -0.06
    -spec
    -0.06
     понять
    -0.06
    Β
    -0.06
     같다
    -0.06
    〉
    -0.06
     теж
    -0.06
    Words
    -0.06
     dục
    -0.06
    POSITIVE LOGITS
    lamak
    0.07
    rtle
    0.07
     Crowley
    0.07
     理
    0.06
    ảng
    0.06
    .Handled
    0.06
    .endsWith
    0.06
    anson
    0.06
     heavenly
    0.06
     xyz
    0.06
    Act Density 0.003%

    No Known Activations