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

    Neuronpedia

    INDEX
    Explanations

    a number or a rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кция
    0.49
    𠃊
    0.46
     soprav
    0.46
    ラベル
    0.45
    ୮
    0.44
    cę
    0.43
     elevationMap
    0.42
    ികളും
    0.42
     தெரிவித்துள்ளது
    0.42
    ரீ
    0.41
    POSITIVE LOGITS
    :
    0.43
     known
    0.42
    we
    0.41
    我知道
    0.40
     defied
    0.39
     defy
    0.38
     parfaite
    0.38
     cleared
    0.38
     Design
    0.38
     unrival
    0.38
    Act Density 0.010%

    No Known Activations