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

    Neuronpedia

    INDEX
    Explanations

    movie and show titles

    oai_token-act-pair · gemini-2.0-flash

    Anime/Sentai series

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.75
     مرئيه
    -0.75
    expandindo
    -0.73
    MigrationBuilder
    -0.73
     propOrder
    -0.72
    CloseOperation
    -0.71
     विश्वसनीयता
    -0.70
     Administrativna
    -0.69
     Signalez
    -0.68
    IsMutable
    -0.66
    POSITIVE LOGITS
    }{*}{
    0.51
     Nani
    0.44
     AudioClip
    0.42
     Playhouse
    0.41
     Ghat
    0.41
     Akira
    0.40
     chiếu
    0.38
    abestanden
    0.38
    subplots
    0.37
     Shiro
    0.37
    Act Density 7.966%

    No Known Activations