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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing floating-point or decimal values (i.e. continuous real-number measurements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     motorcycles
    -0.07
     แล
    -0.07
    raz
    -0.07
    _warning
    -0.07
    CheckBox
    -0.06
    _IGNORE
    -0.06
     baskets
    -0.06
    Stamp
    -0.06
     brief
    -0.06
     Meetings
    -0.06
    POSITIVE LOGITS
     `/
    0.07
     하
    0.07
    holds
    0.07
     EOF
    0.06
    wall
    0.06
     Gaw
    0.06
     vol
    0.06
     mij
    0.06
     nay
    0.06
     dovol
    0.06
    Act Density 0.144%

    No Known Activations