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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash

    This neuron detects the “.” separator used in code (e.g. namespace, class, method, or property accesses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     свое
    -0.07
    .TrimSpace
    -0.07
     fontsize
    -0.06
    createClass
    -0.06
     MUSIC
    -0.06
     quadratic
    -0.06
     issued
    -0.06
     laps
    -0.06
    .getLogger
    -0.06
    Ô
    -0.06
    POSITIVE LOGITS
    ём
    0.07
     réuss
    0.06
    Thunk
    0.06
    ís
    0.06
    ㅠ
    0.06
     */,↵
    0.06
     isset
    0.06
    _attack
    0.06
    TypeInfo
    0.06
    utan
    0.06
    Act Density 0.062%

    No Known Activations