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

    Neuronpedia

    INDEX
    Explanations

    what you're looking for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.52
    एल
    0.50
    न
    0.48
    pples
    0.48
     industrialists
    0.47
    N
    0.46
     গিয়েছিলাম
    0.45
    एनएल
    0.45
    एम
    0.44
    H
    0.44
    POSITIVE LOGITS
     of
    0.55
     subtly
    0.52
     modele
    0.50
     while
    0.48
     edition
    0.48
     leaderboard
    0.47
     scen
    0.47
     dotyczą
    0.47
     wheelchair
    0.46
     framework
    0.46
    Act Density 0.000%

    No Known Activations