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

    Neuronpedia

    INDEX
    Explanations

    vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    je
    1.40
     qilish
    1.40
     pratiquer
    1.34
               
    1.33
    yan
    1.32
     travailler
    1.31
            
    1.30
     permettre
    1.29
     রসের
    1.27
    न्या
    1.27
    POSITIVE LOGITS
    )),
    1.32
    )]
    1.30
    に取り組
    1.25
    ),
    1.23
    から
    1.22
     Deja
    1.22
    ㅛ
    1.22
    )).
    1.20
     Бү
    1.18
     BlogPost
    1.18
    Act Density 0.004%

    No Known Activations