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

    Neuronpedia

    INDEX
    Explanations

    approximate distances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vit
    0.33
     Design
    0.33
     YAML
    0.32
    承包
    0.32
     свойства
    0.31
     Body
    0.31
    ভাগ
    0.31
    কেউ
    0.31
     आत्म
    0.31
     Packaging
    0.31
    POSITIVE LOGITS
    distances
    0.59
     distances
    0.58
     distante
    0.57
     distance
    0.54
     distanza
    0.53
     distancia
    0.52
    Distance
    0.51
    distance
    0.51
     distância
    0.50
     distant
    0.48
    Act Density 0.010%

    No Known Activations