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

    Neuronpedia

    INDEX
    Explanations

    account information or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.56
     etc
    0.44
     kleiner
    0.44
     kle
    0.43
     Ann
    0.43
     manners
    0.42
     pages
    0.41
     mild
    0.41
     jó
    0.41
    waj
    0.40
    POSITIVE LOGITS
    プロジェクト
    0.57
    ネットワーク
    0.57
     ಕ್ಷೇತ್ರ
    0.55
     проекту
    0.52
     цен
    0.51
    િયન
    0.50
    娛
    0.50
    Tabuleiro
    0.49
     பயிற்சி
    0.49
     કોઈપણ
    0.49
    Act Density 0.006%

    No Known Activations