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

    Neuronpedia

    INDEX
    Explanations

    say "forward"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蕰
    -0.08
    anon
    -0.08
    بار
    -0.07
    Drug
    -0.07
    <option
    -0.07
     сторон
    -0.07
    🎬
    -0.07
    -0.07
    隨
    -0.06
    骧
    -0.06
    POSITIVE LOGITS
    Advanced
    0.07
    葜
    0.07
     seeker
    0.07
     Reading
    0.07
     Avg
    0.07
    柯
    0.07
    FileStream
    0.07
    Undo
    0.07
    دى
    0.07
    Certificate
    0.07
    Act Density 0.000%

    No Known Activations