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

    Neuronpedia

    INDEX
    Explanations

    configuration setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.25
    ль
    1.17
     Biotech
    1.16
    प
    1.15
     Implementation
    1.15
     EMB
    1.14
     Winner
    1.12
    文中
    1.08
    াবল
    1.03
     Accelerated
    1.02
    POSITIVE LOGITS
    اں
    1.20
     sebaik
    1.16
    acjach
    1.14
    ⠉
    1.10
     chern
    1.09
    峮
    1.09
    naires
    1.09
    introspection
    1.07
     trauer
    1.07
    wget
    1.06
    Act Density 0.001%

    No Known Activations