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

    Neuronpedia

    INDEX
    Explanations

    numbers as words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⃣
    1.45
    9
    1.23
    ️⃣
    1.21
    7
    1.17
    4
    1.16
    6
    1.14
    th
    1.14
    8
    1.14
    0
    1.14
    一方
    1.14
    POSITIVE LOGITS
     thousand
    1.10
     hundred
    1.09
     availed
    0.98
    ième
    0.94
    uptime
    0.94
     dollars
    0.94
    ishes
    0.91
    тор
    0.88
    uate
    0.84
    atively
    0.84
    Act Density 0.163%

    No Known Activations