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

    Neuronpedia

    INDEX
    Explanations

    describing how something sounds or is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    求め
    0.46
     southwestern
    0.44
     mated
    0.44
    たら
    0.42
     प्राइवेट
    0.42
     tiled
    0.42
     Commander
    0.41
     Australian
    0.41
    システム
    0.41
    Australian
    0.41
    POSITIVE LOGITS
     vollständ
    0.47
    ."],
    0.45
    enthal
    0.42
     sieben
    0.42
     neun
    0.42
    Einstellungen
    0.42
     gleichen
    0.41
    حض
    0.41
    .],
    0.41
    ʼ
    0.40
    Act Density 0.001%

    No Known Activations