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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens containing decimal-point numbers (i.e. floating-point numeric values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ferry
    -0.07
     �
    -0.06
    .Schedule
    -0.06
    _accuracy
    -0.06
     év
    -0.06
     ش
    -0.06
     Entire
    -0.06
    �
    -0.06
     asian
    -0.06
    bucket
    -0.06
    POSITIVE LOGITS
    Xã
    0.07
     urges
    0.07
    =====
    0.06
    ///↵↵
    0.06
    QUIRED
    0.06
    ',{'
    0.06
     monthly
    0.06
    ्ठ
    0.06
    rieving
    0.06
    ापस
    0.06
    Act Density 0.179%

    No Known Activations