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

    Neuronpedia

    INDEX
    Explanations

    vision transformers and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mapping
    0.47
    Visual
    0.43
    visually
    0.43
    mapping
    0.41
    Match
    0.40
    hooter
    0.40
     visualize
    0.40
     визуа
    0.40
    美术
    0.40
    𝚛
    0.40
    POSITIVE LOGITS
     systems
    0.52
     системы
    0.44
     sistemi
    0.44
     cape
    0.42
     Gainesville
    0.41
     系统
    0.41
     biofuel
    0.41
     biofuels
    0.40
     시스템
    0.40
     crisis
    0.40
    Act Density 0.010%

    No Known Activations