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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on JavaScript dotted property‐access or method‐call sequences (e.g. object.method chaining).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apture
    -0.07
    	layer
    -0.07
    켜
    -0.07
    getSource
    -0.06
     دولتی
    -0.06
    SOLE
    -0.06
    ，却
    -0.06
    .Score
    -0.06
    Assignable
    -0.06
     Starr
    -0.06
    POSITIVE LOGITS
     Inch
    0.06
    (numero
    0.06
    ``↵
    0.06
    Gün
    0.06
     inch
    0.06
    �
    0.06
    unto
    0.06
    [W
    0.06
    SYNC
    0.06
     #"
    0.06
    Act Density 0.011%

    No Known Activations