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

    Neuronpedia

    INDEX
    Explanations

    event types and handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ម្ល
    0.44
    visual
    0.42
    ྩ
    0.40
    textured
    0.40
    mix
    0.40
    image
    0.39
    layouts
    0.38
    impose
    0.38
    รู้จัก
    0.38
     ferrite
    0.38
    POSITIVE LOGITS
     Event
    1.11
     event
    1.06
    Event
    1.00
     Ereign
    0.96
    EventType
    0.96
     eventos
    0.96
     EVENT
    0.95
     evento
    0.95
     事件
    0.91
     इवेंट
    0.89
    Act Density 0.012%

    No Known Activations