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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ons
    -0.08
     skup
    -0.08
     перера
    -0.08
     zomaar
    -0.08
    三区
    -0.07
    纽
    -0.07
    .mass
    -0.07
     concaten
    -0.07
    руп
    -0.07
     tiếp
    -0.07
    POSITIVE LOGITS
     높
    0.09
    -weather
    0.08
    timeofday
    0.08
     Shadows
    0.08
     počas
    0.08
     school's
    0.08
     learners
    0.08
     छात्रों
    0.08
    -about
    0.08
     students
    0.08
    Act Density 0.005%

    No Known Activations