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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    έρει
    -0.08
     eating
    -0.07
     send
    -0.07
    riting
    -0.07
    (Main
    -0.07
     include
    -0.06
     performers
    -0.06
    Formatter
    -0.06
     feature
    -0.06
    ride
    -0.06
    POSITIVE LOGITS
    (gcf
    0.06
    Cla
    0.06
    ızı
    0.06
     он
    0.06
    ظٹط
    0.06
     new
    0.06
    nego
    0.06
     첫
    0.06
    Cheap
    0.06
     Аль
    0.06
    Act Density 0.020%

    No Known Activations