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

    Neuronpedia

    INDEX
    Explanations

    answer to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sec
    0.74
    zący
    0.72
    点の
    0.71
     genel
    0.71
    зю
    0.70
     看
    0.70
    pxy
    0.69
    letek
    0.68
     arraigned
    0.68
     جات
    0.67
    POSITIVE LOGITS
     full
    0.73
    ത്തക
    0.70
    Full
    0.67
    full
    0.67
    FULL
    0.67
     FULL
    0.66
     questions
    0.66
     जितना
    0.65
    Ƅ
    0.64
    dispatchEvent
    0.62
    Act Density 0.008%

    No Known Activations