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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron detects the leading asterisk markers used in Java Javadoc-style block comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Course
    -0.07
    框
    -0.06
     cửa
    -0.06
    ấy
    -0.06
    Hours
    -0.06
    383
    -0.06
    _adj
    -0.06
    onse
    -0.06
     Triangle
    -0.06
     répond
    -0.06
    POSITIVE LOGITS
     gł
    0.06
    passport
    0.06
     Emb
    0.06
     authenticate
    0.06
     Esk
    0.06
    tplib
    0.06
     orderby
    0.06
     stealing
    0.06
     Βασ
    0.06
     ##
    0.06
    Act Density 0.007%

    No Known Activations