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

    Neuronpedia

    INDEX
    Explanations

    list items separated by bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lerinden
    0.70
    lerini
    0.64
    lerden
    0.62
    larından
    0.62
    cultured
    0.57
    lier
    0.57
    larına
    0.57
    larını
    0.54
    soci
    0.54
    tarif
    0.54
    POSITIVE LOGITS
     are
    0.61
     ermöglicht
    0.60
     has
    0.56
     refers
    0.55
     hanno
    0.54
     valamint
    0.54
     instalação
    0.54
     encontrarás
    0.54
     sämt
    0.53
     ermöglichen
    0.53
    Act Density 0.001%

    No Known Activations