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

    Neuronpedia

    INDEX
    Explanations

    landing page prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्यापारियों
    0.48
    Instagram
    0.43
     vignettes
    0.42
    LinkedIn
    0.41
    toxic
    0.41
    旗
    0.41
    indexes
    0.39
     instagram
    0.39
     roche
    0.39
     Fácil
    0.39
    POSITIVE LOGITS
     ui
    0.47
     UI
    0.45
    UI
    0.40
     নিল
    0.37
     Optical
    0.37
     app
    0.37
    Го
    0.35
     агент
    0.35
     énon
    0.34
     menjaga
    0.34
    Act Density 0.046%

    No Known Activations