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

    Neuronpedia

    INDEX
    Explanations

    create and manage animations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     εισ
    0.80
     soov
    0.77
     gelegt
    0.74
     Tras
    0.74
     Haziran
    0.74
     Inher
    0.74
     вули
    0.73
     Poss
    0.73
     Бе
    0.73
     oktober
    0.72
    POSITIVE LOGITS
    appan
    0.74
    spersed
    0.73
    à
    0.71
    до
    0.69
    warm
    0.68
    셈
    0.67
    เกิด
    0.67
    яви
    0.67
     абсолю
    0.66
    lists
    0.65
    Act Density 0.000%

    No Known Activations