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
    ,$_
    -0.07
    _distances
    -0.06
    
    -0.06
    -news
    -0.06
    (points
    -0.06
    "]]↵
    -0.06
     annex
    -0.06
    ,unsigned
    -0.06
     quote
    -0.06
     bbc
    -0.06
    POSITIVE LOGITS
     Pháp
    0.07
    (patient
    0.07
     aroused
    0.06
     الم
    0.06
    -factor
    0.06
    遭
    0.06
     led
    0.06
     ارز
    0.06
    -J
    0.06
     Crowley
    0.06
    Act Density 0.003%

    No Known Activations