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

    Neuronpedia

    INDEX
    Explanations

    minified code

    oai_token-act-pair · gemini-2.0-flash

    code/non-english

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.60
    (;;)
    -0.58
     pescoço
    -0.57
    Personendaten
    -0.57
    UnsafeEnabled
    -0.56
    ayaquil
    -0.55
    NameInMap
    -0.54
    :✨
    -0.53
     élé
    -0.50
    enziali
    -0.50
    POSITIVE LOGITS
    पया
    0.54
    Примечания
    0.54
     AssemblyCulture
    0.52
    torie
    0.51
    》.
    0.50
    ---*/
    0.48
     везе
    0.47
     />";
    0.47
    Liên
    0.47
    ASMA
    0.44
    Act Density 4.590%

    No Known Activations