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

    Neuronpedia

    INDEX
    Explanations

    subtitles/titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Love
    -0.07
    る
    -0.06
     recogn
    -0.06
     von
    -0.06
    HOOK
    -0.06
     scape
    -0.06
     نیرو
    -0.06
    ของผ
    -0.06
    Log
    -0.06
     renov
    -0.06
    POSITIVE LOGITS
    -condition
    0.07
    Seeder
    0.07
     subtitles
    0.07
     utiliser
    0.07
    ICI
    0.07
    datal
    0.07
     recurring
    0.06
     Sub
    0.06
    Orth
    0.06
    （笑
    0.06
    Act Density 0.002%

    No Known Activations