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

    Neuronpedia

    INDEX
    Explanations

    certain properties or requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     learnings
    0.46
     dach
    0.44
     mandrel
    0.44
    breakpoint
    0.43
     постара
    0.43
     caul
    0.42
     monster
    0.42
    AllWindows
    0.41
     every
    0.41
     ojos
    0.41
    POSITIVE LOGITS
     vissa
    0.49
     некоторых
    0.47
    某些
    0.47
     некоторые
    0.46
     certain
    0.44
     bepaalde
    0.44
    कुछ
    0.43
     tertentu
    0.42
     Degrees
    0.42
     Certain
    0.41
    Act Density 0.003%

    No Known Activations