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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sm
    -0.08
    _lists
    -0.07
     yeme
    -0.07
     Lista
    -0.06
     noting
    -0.06
    шли
    -0.06
    _threads
    -0.06
    ]*
    -0.06
    tot
    -0.06
     Pharma
    -0.06
    POSITIVE LOGITS
     Υ
    0.06
     retrofit
    0.06
    ?↵↵↵↵↵↵
    0.06
    _ENDIAN
    0.06
    (struct
    0.06
     المغ
    0.06
    .AUTH
    0.06
     Ссылки
    0.06
     Quaternion
    0.06
    ＠
    0.06
    Act Density 0.286%

    No Known Activations