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

    Neuronpedia

    INDEX
    Explanations

    the context of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itzar
    0.88
     situ
    0.81
    ábban
    0.79
     čak
    0.78
    ንስ
    0.78
     हैरानी
    0.74
     mellan
    0.74
    рона
    0.72
    ๋ยว
    0.72
    üedad
    0.70
    POSITIVE LOGITS
     context
    1.80
     light
    1.53
     контек
    1.53
    context
    1.52
     contexts
    1.51
     Context
    1.42
     contexto
    1.40
     Light
    1.40
     framework
    1.35
    Light
    1.34
    Act Density 0.054%

    No Known Activations