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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of distances given in “light-years.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Detected
    -0.07
    .banner
    -0.06
    ۱
    -0.06
     svém
    -0.06
    _Title
    -0.06
    _activate
    -0.06
    but
    -0.06
    Ot
    -0.06
     fak
    -0.06
    bank
    -0.06
    POSITIVE LOGITS
     Fiesta
    0.07
    ngrx
    0.06
    Lisa
    0.06
     wind
    0.06
     Wrestling
    0.06
     lawsuits
    0.06
     −
    0.06
     $_[
    0.06
     Christoph
    0.06
     pri
    0.06
    Act Density 0.002%

    No Known Activations