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 Java source code documentation blocks, i.e. lines of JavaDoc comments (the “* …” comment lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    енном
    -0.07
    .yellow
    -0.07
     Ginger
    -0.07
    ця
    -0.06
    Recommend
    -0.06
    tout
    -0.06
    ador
    -0.06
     faucet
    -0.06
    rench
    -0.06
    برای
    -0.06
    POSITIVE LOGITS
     /**↵
    0.08
    /**↵
    0.08
     arising
    0.07
    /*!↵
    0.07
    .flow
    0.07
     hardly
    0.06
     언어
    0.06
    _DF
    0.06
    POST
    0.06
    จำนวน
    0.06
    Act Density 0.007%

    No Known Activations