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

    Neuronpedia

    INDEX
    Explanations

    Retrieved from URLs or sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    獷
    0.43
     addObject
    0.41
     biomass
    0.40
     дово
    0.39
     memoirs
    0.38
    ITERATURE
    0.36
     تنفيذ
    0.36
     biochemical
    0.35
     zbior
    0.35
     각각
    0.35
    POSITIVE LOGITS
     tiered
    0.40
     https
    0.38
     auprès
    0.37
     Nearly
    0.37
    openai
    0.37
     بیل
    0.37
     Academy
    0.37
    났다
    0.36
    getModel
    0.36
     Grades
    0.35
    Act Density 0.005%

    No Known Activations