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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, identifying numbers (including integers and decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     },
    -0.07
    '},
    -0.07
     Origin
    -0.06
    variants
    -0.06
    _Tag
    -0.06
    >');
    -0.06
    .StatusBadRequest
    -0.06
     unavailable
    -0.06
    _TYP
    -0.06
     Ridley
    -0.06
    POSITIVE LOGITS
     يمكن
    0.07
     BEGIN
    0.07
    eydi
    0.06
     tvoří
    0.06
    něž
    0.06
    >n
    0.06
     jeden
    0.06
     vandal
    0.06
      ↵
    0.06
     прям
    0.06
    Act Density 0.059%

    No Known Activations