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

    Neuronpedia

    INDEX
    Explanations

    FDIC, Azure, mixer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vasena
    1.27
    UIServer
    1.27
    راط
    1.25
    кл
    1.21
    ForSettings
    1.15
    荃灣
    1.12
    لاین
    1.12
     தவ
    1.11
    вър
    1.10
    ToJava
    1.10
    POSITIVE LOGITS
     một
    1.60
     einen
    1.56
     eine
    1.48
     quelques
    1.47
     qualche
    1.43
     sebuah
    1.41
     quello
    1.41
     isang
    1.34
    一個
    1.33
     deux
    1.29
    Act Density 0.288%

    No Known Activations