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

    Neuronpedia

    INDEX
    Explanations

    codes, SIP, routing, spiritual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Concini
    0.45
    ැනි
    0.43
    consciousness
    0.41
    твори
    0.40
    Foreground
    0.39
    ConsoleText
    0.39
    ጠበ
    0.39
    Fern
    0.39
    VAE
    0.39
    쟈
    0.39
    POSITIVE LOGITS
     тоже
    0.45
     routing
    0.45
     placés
    0.44
     calling
    0.44
     directs
    0.43
     destroys
    0.43
     pourcentage
    0.43
     Dataset
    0.43
     reps
    0.42
     баскетбол
    0.42
    Act Density 0.157%

    No Known Activations