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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on backtick tokens, i.e. the Markdown inline-code and code-fence delimiters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    illary
    -0.07
    λευ
    -0.06
     refreshing
    -0.06
    _THRESHOLD
    -0.06
    -flow
    -0.06
    _ADC
    -0.06
     underground
    -0.06
    اهش
    -0.06
    -java
    -0.06
    лада
    -0.06
    POSITIVE LOGITS
     средств
    0.07
    .support
    0.07
    resse
    0.06
    _outputs
    0.06
    顶
    0.06
    .tc
    0.06
     position
    0.06
     khóa
    0.06
     constructs
    0.06
     Вар
    0.06
    Act Density 0.032%

    No Known Activations