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

    Neuronpedia

    INDEX
    Explanations

    colors and patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MgCl
    1.26
     ਲਈ
    1.24
    iduría
    1.23
     kaldığımız
    1.23
    िंग
    1.21
    ال
    1.20
    uels
    1.18
    侸
    1.16
     utilisés
    1.14
     arrêter
    1.14
    POSITIVE LOGITS
    _
    1.34
    ed
    1.31
     haired
    1.31
    ),
    1.27
    a
    1.27
    d
    1.23
    ).
    1.20
    ্ড
    1.18
     generation
    1.18
    )
    1.14
    Act Density 0.258%

    No Known Activations