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

    Neuronpedia

    INDEX
    Explanations

    potential danger or risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ני
    0.47
    ީ
    0.46
    になって
    0.44
    ަ
    0.43
     transduction
    0.42
    ަކ
    0.42
     Samar
    0.40
    損
    0.40
    աք
    0.40
     الجديدة
    0.40
    POSITIVE LOGITS
     escritor
    0.46
    rakech
    0.46
     straws
    0.46
     Cliquez
    0.45
     ಬಿಯ
    0.44
     mengucapkan
    0.44
     অনুসারে
    0.43
    同学
    0.43
    HAEL
    0.43
     hyvä
    0.43
    Act Density 0.001%

    No Known Activations