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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric constants and related arithmetic tokens (digits and operators) in math expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     antibiot
    -0.08
     Soc
    -0.07
     prec
    -0.07
    etí
    -0.06
    PropertyValue
    -0.06
     prix
    -0.06
    _argument
    -0.06
    رس
    -0.06
    Pipeline
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
     assort
    0.07
    ButtonClick
    0.07
     Flavor
    0.07
    esinin
    0.06
    Sampling
    0.06
     soaring
    0.06
     complete
    0.06
    *",
    0.06
     borderColor
    0.06
    Complete
    0.06
    Act Density 0.002%

    No Known Activations