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

    Neuronpedia

    INDEX
    Explanations

    colon punctuation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    话说
    -0.07
    _BIG
    -0.06
    	errors
    -0.06
     />)↵
    -0.06
    不得不
    -0.06
    -\
    -0.06
     הי
    -0.06
     NPR
    -0.06
    长大
    -0.06
     stood
    -0.06
    POSITIVE LOGITS
    _EQUAL
    0.07
    ivamente
    0.07
    guard
    0.07
    _THAN
    0.07
    进展
    0.07
    awa
    0.06
    subpackage
    0.06
     acordo
    0.06
    Fuse
    0.06
    udiantes
    0.06
    Act Density 0.021%

    No Known Activations