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

    Neuronpedia

    INDEX
    Explanations

    Num

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric literal tokens (especially floating‐point constants) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [N
    -0.07
    	index
    -0.07
    export
    -0.06
     شم
    -0.06
    )|
    -0.06
    [C
    -0.06
    mand
    -0.06
    *self
    -0.06
    (this
    -0.06
    nesty
    -0.06
    POSITIVE LOGITS
    obel
    0.07
     právní
    0.06
    ULO
    0.06
    _ComCallableWrapper
    0.06
     Postal
    0.06
     formulario
    0.06
     Submit
    0.06
     것도
    0.06
     医
    0.06
    ORT
    0.06
    Act Density 0.043%

    No Known Activations