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

    Neuronpedia

    INDEX
    Explanations

    describing technical terms and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    羽根
    0.45
    ាម
    0.41
    CONDS
    0.41
     anses
    0.41
    ރު
    0.39
    ﺄ
    0.38
    𝙪
    0.38
    තිය
    0.38
    ెంట్‌
    0.38
    輋
    0.38
    POSITIVE LOGITS
    with
    0.34
     工程
    0.34
    ordin
    0.34
     Read
    0.34
    ску
    0.33
    Read
    0.33
    বিত্র
    0.33
     Opens
    0.33
     even
    0.33
    0.33
    Act Density 0.000%

    No Known Activations