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

    Neuronpedia

    INDEX
    Explanations

    emojis and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Detach
    1.18
    用
    1.13
     Sitz
    1.11
    大
    1.07
     Estes
    1.05
     sắt
    1.04
    c
    1.03
    夲
    1.02
     github
    1.01
     supernatants
    1.01
    POSITIVE LOGITS
    sic
    1.33
    ллина
    1.14
    iation
    1.14
     wrinkle
    1.13
    ─
    1.10
    ೀಯ
    1.07
    ్వ
    1.06
     precluded
    1.05
     quieter
    1.04
    poss
    1.03
    Act Density 0.000%

    No Known Activations