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

    Neuronpedia

    INDEX
    Explanations

    conversations or accept larger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     únicamente
    0.53
     Bhagavato
    0.50
     которых
    0.49
     Idani
    0.48
     ऑक्स
    0.48
     толькі
    0.48
     esclusivamente
    0.47
     کھی
    0.47
     solamente
    0.47
     kte
    0.46
    POSITIVE LOGITS
    ,
    0.49
    -
    0.45
      
    0.45
     markets
    0.44
     variety
    0.43
     discs
    0.42
    two
    0.42
    “,
    0.42
    צ
    0.42
    Haw
    0.41
    Act Density 0.008%

    No Known Activations