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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     잘
    -0.07
    _POS
    -0.07
     Для
    -0.06
    _AS
    -0.06
    alsy
    -0.06
    _VALUES
    -0.06
    abr
    -0.06
    Files
    -0.06
     教
    -0.06
     HIT
    -0.06
    POSITIVE LOGITS
    Either
    0.06
    ($('
    0.06
     môi
    0.06
     Feast
    0.06
     चक
    0.06
     Modular
    0.06
     cannabin
    0.06
    @"↵
    0.06
    ?>"><?
    0.06
     Marion
    0.06
    Act Density 0.032%

    No Known Activations