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

    Neuronpedia

    INDEX
    Explanations

    start of block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chromospheres
    1.02
     clowns
    0.89
     gobl
    0.88
     melodies
    0.86
     Anime
    0.85
     headwinds
    0.84
     Twitch
    0.83
     spies
    0.83
     sins
    0.82
     кү
    0.82
    POSITIVE LOGITS
    ل
    1.06
    І
    0.92
    Lors
    0.83
    А
    0.83
    ال
    0.78
    Esta
    0.78
    Ir
    0.78
    хі
    0.76
    র
    0.76
    म
    0.76
    Act Density 0.002%

    No Known Activations