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

    Neuronpedia

    INDEX
    Explanations

    fossil

    np_max-act · gemini-2.0-flash

    The neuron fires on words related to paleontology and fossilization (e.g., “paleontology,” “fossil,” “fossilized,” “fossilization”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Swarm
    -0.07
     příč
    -0.07
     rowCount
    -0.07
     Ν
    -0.07
     various
    -0.06
    //!↵
    -0.06
    _hex
    -0.06
     Combo
    -0.06
     speaker
    -0.06
    acts
    -0.06
    POSITIVE LOGITS
     fossil
    0.13
     fossils
    0.12
    ossil
    0.09
    ’я
    0.07
     Etsy
    0.07
     Essential
    0.07
     предел
    0.07
     fost
    0.07
     postfix
    0.07
     Boss
    0.07
    Act Density 0.002%

    No Known Activations