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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⃣
    1.56
    ️⃣
    1.55
    ب
    1.50
     dozen
    1.48
     litres
    1.37
    து
    1.33
    त
    1.33
    ন
    1.33
    ths
    1.28
     liters
    1.24
    POSITIVE LOGITS
    stion
    1.15
    اس
    1.09
    diethyl
    1.08
    𝓮
    1.07
    ların
    1.04
    燵
    1.03
    و
    0.99
    arının
    0.97
    ulloch
    0.95
    ামী
    0.91
    Act Density 0.255%

    No Known Activations