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

    Neuronpedia

    INDEX
    Explanations

    end of list punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outcrop
    0.34
    .",
    0.30
    .',
    0.30
    urned
    0.30
     Phila
    0.30
     vasculature
    0.29
     stoichi
    0.29
     Watertown
    0.29
     Cargill
    0.29
     ANON
    0.29
    POSITIVE LOGITS
     इत्यादी
    0.35
     etc
    0.35
     пя
    0.33
    等等
    0.30
     ….
    0.30
     комбина
    0.30
     …
    0.29
    â
    0.29
     semuanya
    0.29
    о
    0.29
    Act Density 0.295%

    No Known Activations