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

    Neuronpedia

    INDEX
    Explanations

    1-800-656-HOPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बनने
    0.40
     पब्लिक
    0.40
    资
    0.39
    考虑
    0.38
    पाठी
    0.37
    icit
    0.37
    郘
    0.37
    ymax
    0.36
    考慮
    0.36
    ième
    0.36
    POSITIVE LOGITS
    Ho
    0.68
     Ho
    0.68
     ho
    0.67
    izontal
    0.63
    ホ
    0.63
     호
    0.63
     हो
    0.61
     ہو
    0.61
     ホ
    0.61
    ho
    0.59
    Act Density 0.011%

    No Known Activations