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
    "F
    -0.07
     欧美
    -0.07
    енную
    -0.06
     आ
    -0.06
    toBeInTheDocument
    -0.06
     JA
    -0.06
     fino
    -0.06
    BoundingBox
    -0.06
    uz
    -0.06
    уз
    -0.06
    POSITIVE LOGITS
    mlin
    0.07
    itted
    0.07
    irit
    0.06
     {*
    0.06
    /admin
    0.06
    arith
    0.06
     {}.
    0.06
    /am
    0.06
     أح
    0.06
    .dict
    0.06
    Act Density 0.014%

    No Known Activations