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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -slide
    -0.07
    occus
    -0.06
     refill
    -0.06
    权限
    -0.06
     primera
    -0.06
    	layer
    -0.06
    -arrow
    -0.06
     memories
    -0.06
    IID
    -0.06
    Terms
    -0.06
    POSITIVE LOGITS
    	inst
    0.07
     wchar
    0.07
     chy
    0.06
    _DIFF
    0.06
    чают
    0.06
    _interaction
    0.06
     jed
    0.06
    rawtypes
    0.06
    อเม
    0.06
     pří
    0.06
    Act Density 0.002%

    No Known Activations