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

    Neuronpedia

    INDEX
    Explanations

    varied topics

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens—years, dates, and other numbers (numerals).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    lt
    -0.07
     righteous
    -0.07
    Asc
    -0.07
    кие
    -0.06
    .genre
    -0.06
    啪
    -0.06
    -resistant
    -0.06
     것
    -0.06
     підт
    -0.06
    _code
    -0.06
    POSITIVE LOGITS
    .AspNetCore
    0.06
    :"",
    0.06
     kari
    0.06
     Sean
    0.06
     празд
    0.06
     shaders
    0.06
    пра
    0.06
     >::
    0.06
    _numeric
    0.05
     atrib
    0.05
    Act Density 0.269%

    No Known Activations