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

    Neuronpedia

    INDEX
    Explanations

    Baseball draft years

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—years, ages, statistical figures, and other numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     accessor
    -0.06
    res
    -0.06
     Swan
    -0.06
    /current
    -0.06
    -dev
    -0.06
    >);↵
    -0.06
     ilişkin
    -0.06
    culate
    -0.06
    ashing
    -0.06
     Casey
    -0.06
    POSITIVE LOGITS
     werk
    0.06
    	IN
    0.06
     skewed
    0.06
    isLoading
    0.06
     متخصص
    0.06
    (entries
    0.06
    ęk
    0.06
    ağ
    0.06
    FAIL
    0.06
     GLUT
    0.06
    Act Density 0.011%

    No Known Activations