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

    Neuronpedia

    INDEX
    Explanations

    agreement/consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ое
    -0.07
    ft
    -0.07
     '↵↵
    -0.07
     caract
    -0.06
     vice
    -0.06
    CppGenericClass
    -0.06
    _start
    -0.06
    onder
    -0.06
    Defaults
    -0.06
     fak
    -0.06
    POSITIVE LOGITS
    iverz
    0.06
     HVAC
    0.06
     χω
    0.06
    ają
    0.06
    воб
    0.06
    .estado
    0.06
     نماز
    0.06
    tığını
    0.06
     aqu
    0.06
     Driving
    0.06
    Act Density 0.024%

    No Known Activations