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

    Neuronpedia

    INDEX
    Explanations

    trim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     છેલ્લા
    0.48
     karya
    0.47
     त्यानुसार
    0.45
     त्यासाठी
    0.45
     GSM
    0.43
    тился
    0.43
     camada
    0.43
    രിച്ചത്
    0.42
     Grâce
    0.42
    нути
    0.42
    POSITIVE LOGITS
    ON
    0.59
    وسک
    0.49
    án
    0.48
    ó
    0.42
    ong
    0.41
     muddy
    0.41
    窕
    0.41
    san
    0.41
     ás
    0.39
     gleiche
    0.39
    Act Density 0.001%

    No Known Activations