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

    Neuronpedia

    INDEX
    Explanations

    titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ധി
    0.47
    offsetof
    0.43
    què
    0.39
    Ᏻ
    0.36
     sei
    0.35
    jalan
    0.35
    ,</
    0.34
    日至
    0.34
    સે
    0.34
     mengingat
    0.34
    POSITIVE LOGITS
     শীর্ষক
    0.95
     című
    0.93
    という
    0.83
    이라는
    0.80
     అనే
    0.79
     라는
    0.77
     नामक
    0.76
     adlı
    0.72
    라는
    0.69
    するという
    0.69
    Act Density 0.100%

    No Known Activations