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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Johan
    -0.07
     gaussian
    -0.07
     Deus
    -0.06
    .lesson
    -0.06
    _script
    -0.06
     entropy
    -0.06
    XX
    -0.06
    _nt
    -0.06
     keyword
    -0.06
     gems
    -0.06
    POSITIVE LOGITS
    стро
    0.07
    �
    0.06
     Qualified
    0.06
    -covered
    0.06
    .avi
    0.06
    wid
    0.06
     Wireless
    0.06
     Providing
    0.06
    ilde
    0.06
    ל
    0.05
    Act Density 0.002%

    No Known Activations