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

    Neuronpedia

    INDEX
    Explanations

    hugging face pipeline usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *}$
    0.38
    நட
    0.37
    ellia
    0.35
    ดูแล
    0.35
     murdered
    0.35
    贈り
    0.35
    fony
    0.35
    رخ
    0.34
    उनकी
    0.34
     लक्षात
    0.34
    POSITIVE LOGITS
     Stoff
    0.41
     reviving
    0.40
     Mach
    0.40
     revive
    0.39
     Provider
    0.39
    িকে
    0.39
     revived
    0.39
     ROS
    0.37
     Endpoint
    0.37
     ঘাট
    0.37
    Act Density 0.002%

    No Known Activations