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

    Neuronpedia

    INDEX
    Explanations

    Human vs. Machine contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Properties
    -0.07
     аллерг
    -0.06
     Age
    -0.06
    final
    -0.06
     Packages
    -0.06
    ItemType
    -0.06
    ặng
    -0.06
    _ALWAYS
    -0.06
     packages
    -0.06
    Props
    -0.06
    POSITIVE LOGITS
     */,
    0.06
    ="'+
    0.06
    rubu
    0.06
     непосред
    0.06
     lng
    0.06
    يون
    0.06
    छ
    0.06
     "\\"
    0.06
    ']=="
    0.06
     cuz
    0.06
    Act Density 0.082%

    No Known Activations