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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ώς
    -0.08
    *******↵
    -0.08
    烟
    -0.06
    Address
    -0.06
    html
    -0.06
    па
    -0.06
    ındır
    -0.06
    发
    -0.06
    تیب
    -0.06
     dzi
    -0.06
    POSITIVE LOGITS
    thumbs
    0.06
     Covid
    0.06
    ouis
    0.06
     Calif
    0.06
     Hurricanes
    0.06
     Solid
    0.06
    "She
    0.06
     weakest
    0.06
    _checkpoint
    0.06
     pressured
    0.06
    Act Density 0.169%

    No Known Activations