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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なし
    -0.07
    isters
    -0.06
    ünü
    -0.06
    ối
    -0.06
     cited
    -0.06
    、大
    -0.06
     Tasmania
    -0.06
    NOT
    -0.06
    ํ
    -0.06
    rane
    -0.06
    POSITIVE LOGITS
     sha
    0.07
     sổ
    0.06
     Gri
    0.06
     veil
    0.06
    ,last
    0.06
     Shawn
    0.06
    _delta
    0.06
     ενός
    0.06
     searchData
    0.06
    _truth
    0.06
    Act Density 0.098%

    No Known Activations