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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <![
    -0.06
     checked
    -0.06
     presented
    -0.06
    -Za
    -0.06
     shady
    -0.06
     لي
    -0.06
     desperate
    -0.05
     oral
    -0.05
    Parents
    -0.05
     pays
    -0.05
    POSITIVE LOGITS
    Row
    0.07
    橋
    0.07
     '"';↵
    0.06
    离开
    0.06
    .Encode
    0.06
     McGill
    0.06
     esteem
    0.06
     hacker
    0.06
     […]↵↵
    0.06
    application
    0.06
    Act Density 0.004%

    No Known Activations