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

    Neuronpedia

    INDEX
    Explanations

    gravity

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to the space environment and gravity (e.g., “space,” “SPACE,” “gravity,” “microgravity”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /**↵↵
    -0.07
     Slov
    -0.06
    ailable
    -0.06
     Skyrim
    -0.06
    unsigned
    -0.06
     SIL
    -0.06
     đáng
    -0.06
     رسول
    -0.06
     सल
    -0.06
     یعنی
    -0.06
    POSITIVE LOGITS
    _Text
    0.07
    asking
    0.07
     proving
    0.07
     reflexivity
    0.07
     refere
    0.07
     nghề
    0.06
    ổng
    0.06
     gravity
    0.06
    quiet
    0.06
     gözlem
    0.06
    Act Density 0.004%

    No Known Activations