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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berman
    -0.07
    manent
    -0.06
     (\
    -0.06
    Alive
    -0.06
    tables
    -0.06
    _negative
    -0.06
    _rw
    -0.06
    buquerque
    -0.06
    duced
    -0.06
     resultMap
    -0.06
    POSITIVE LOGITS
    =_("
    0.07
    áním
    0.07
    "',↵
    0.07
     underage
    0.06
    /{{$
    0.06
    	↵↵
    0.06
     espan
    0.06
     atrib
    0.06
     hardship
    0.06
    _fin
    0.06
    Act Density 0.068%

    No Known Activations