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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convex
    -0.07
    opol
    -0.06
     Lucky
    -0.06
    μη
    -0.06
    amel
    -0.06
     setter
    -0.06
     Ø
    -0.06
    rhs
    -0.06
    DROP
    -0.06
     MMI
    -0.06
    POSITIVE LOGITS
    nám
    0.07
    ポート
    0.07
    目前
    0.06
    营
    0.06
     Caroline
    0.06
     facil
    0.06
    La
    0.06
    (cx
    0.06
     abandonment
    0.06
    ulario
    0.06
    Act Density 0.061%

    No Known Activations