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

    Neuronpedia

    INDEX
    Explanations

    biological/scientific research

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical values (digits, decimal numbers, and measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -health
    -0.07
     health
    -0.07
    -Control
    -0.07
    Prod
    -0.06
     fooled
    -0.06
    yd
    -0.06
     введ
    -0.06
     COLOR
    -0.06
     budete
    -0.06
     मत
    -0.06
    POSITIVE LOGITS
    /autoload
    0.06
     heaps
    0.06
    ||||
    0.06
     القرآن
    0.06
    @register
    0.06
     ging
    0.06
    .lon
    0.06
    +]
    0.06
     WELL
    0.06
     şik
    0.06
    Act Density 0.104%

    No Known Activations