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

    Neuronpedia

    INDEX
    Explanations

    articles with metadata

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens containing a decimal point (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _math
    -0.06
     blow
    -0.06
    Tr
    -0.06
     Ful
    -0.06
    -running
    -0.06
     Sol
    -0.06
     μου
    -0.06
     went
    -0.06
    .Cho
    -0.06
     Bio
    -0.06
    POSITIVE LOGITS
    -distance
    0.08
     interface
    0.07
    少年
    0.07
    Positions
    0.07
     Personality
    0.06
    iề
    0.06
    Collect
    0.06
     زنی
    0.06
     específ
    0.06
     Exception
    0.06
    Act Density 0.016%

    No Known Activations