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

    Neuronpedia

    INDEX
    Explanations

    toys and games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Букмекерская
    0.80
     mahasiswa
    0.79
     деву
    0.78
    🍸
    0.74
     HTTP
    0.74
     Whisky
    0.73
    🚬
    0.72
     whisky
    0.72
     девушки
    0.70
     महाविद्या
    0.70
    POSITIVE LOGITS
     play
    2.41
     toys
    2.36
     playtime
    2.30
     playroom
    2.26
     Play
    2.20
    Play
    2.19
     toy
    2.13
     juguetes
    2.09
     playgrounds
    2.04
     playground
    2.03
    Act Density 0.375%

    No Known Activations