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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric and math‐related tokens, effectively spotting numbers and numerical expressions in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    。「
    -0.08
    妃
    -0.07
     пут
    -0.06
    ucción
    -0.06
    Battery
    -0.06
     Aber
    -0.06
    され
    -0.06
    _EC
    -0.06
     ап
    -0.06
    .ctrl
    -0.06
    POSITIVE LOGITS
    Writable
    0.07
    jem
    0.06
     acknowledgement
    0.06
     pageInfo
    0.06
    ripsi
    0.06
    appropri
    0.06
     تمامی
    0.06
    규
    0.06
    시에
    0.06
    .ศ
    0.06
    Act Density 0.014%

    No Known Activations