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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on the dot (“.”) punctuation used for member access or method chaining in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thaimassage
    -0.07
     *)"
    -0.07
    _BLEND
    -0.07
     съ
    -0.06
    电影
    -0.06
     Builds
    -0.06
    _FATAL
    -0.06
    „V
    -0.06
     万円
    -0.06
     Advisor
    -0.06
    POSITIVE LOGITS
    ีน
    0.06
    ps
    0.06
    ettle
    0.06
     descending
    0.06
    ığı
    0.06
    лы
    0.06
    126
    0.06
     researchers
    0.06
     vistas
    0.06
    ifle
    0.06
    Act Density 0.001%

    No Known Activations