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

    Neuronpedia

    INDEX
    Explanations

    updating positionactivate or executeobject localization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nouvelles
    0.46
     nuevas
    0.45
     interpretations
    0.43
     novas
    0.41
     substance
    0.41
     molds
    0.41
     de
    0.39
     pensamientos
    0.39
     تفسیر
    0.39
     seu
    0.38
    POSITIVE LOGITS
     기존
    0.43
     activating
    0.42
     activate
    0.41
    Boy
    0.41
     सक्रिय
    0.41
     طریق
    0.41
     vorhand
    0.40
     executing
    0.40
    现有
    0.40
     aktif
    0.39
    Act Density 0.044%

    No Known Activations