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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Household
    -0.07
    Box
    -0.07
    bn
    -0.07
     международ
    -0.06
     Flex
    -0.06
     wary
    -0.06
    obox
    -0.06
    계획
    -0.06
    wan
    -0.06
    كتور
    -0.06
    POSITIVE LOGITS
     handgun
    0.06
    _ATTRIB
    0.06
    (gulp
    0.06
    ledge
    0.06
    _deposit
    0.06
    ifdef
    0.06
     Caption
    0.06
    errorMessage
    0.06
    quoise
    0.06
     انتشار
    0.06
    Act Density 0.093%

    No Known Activations