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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     боя
    -0.07
    	sig
    -0.06
     #'
    -0.06
     *>(
    -0.06
    _arrow
    -0.06
    _EQ
    -0.06
     zosta
    -0.06
    ifie
    -0.06
     soubor
    -0.06
    應
    -0.06
    POSITIVE LOGITS
    undred
    0.07
     Chand
    0.07
     unanimous
    0.06
    έλ
    0.06
     ancora
    0.06
    aggi
    0.06
    _supplier
    0.06
    ェ
    0.06
    335
    0.06
    _xx
    0.06
    Act Density 0.007%

    No Known Activations