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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting list‐style structure markers—like numbered items (e.g. “1.”, “2.”), semicolons, and other enumeration cues.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ็ก
    -0.06
    /docs
    -0.06
     závod
    -0.06
    AYS
    -0.06
    _site
    -0.06
    рами
    -0.06
     पड़
    -0.06
     );
↵
↵
    -0.06
     которая
    -0.06
    ůl
    -0.06
    POSITIVE LOGITS
    民
    0.07
     Reliable
    0.06
     reinforcing
    0.06
    งเศส
    0.06
    stellung
    0.06
     Chanel
    0.06
     TEX
    0.06
    _DD
    0.06
    lict
    0.06
     Insider
    0.06
    Act Density 0.010%

    No Known Activations