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

    Neuronpedia

    INDEX
    Explanations

    gold and sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.27
    ן
    1.26
    ان
    1.16
    াল
    1.06
    ال
    1.05
    นำ
    1.05
    はどう
    1.02
    ों
    1.00
    ה
    1.00
    न
    1.00
    POSITIVE LOGITS
    inden
    1.16
    old
    1.14
    od
    1.11
    ü
    1.08
     foliis
    1.02
    oporosis
    1.02
     Daher
    1.00
    ப்படுகிறது
    0.99
     Ancak
    0.98
    ö
    0.97
    Act Density 0.002%

    No Known Activations