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

    Neuronpedia

    INDEX
    Explanations

    introductions and guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मुळे
    1.03
    ক্স
    1.00
     hypothesize
    0.96
     الم
    0.91
    WON
    0.91
     AcOEt
    0.91
    gbm
    0.90
     musée
    0.88
    IONE
    0.87
    ण्यात
    0.86
    POSITIVE LOGITS
    люс
    1.07
    atomy
    1.04
    न
    1.03
    re
    1.00
    one
    1.00
    on
    0.96
    its
    0.96
     lucrat
    0.93
    נו
    0.93
     שלך
    0.91
    Act Density 0.157%

    No Known Activations