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

    Neuronpedia

    INDEX
    Explanations

    command-line options or levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শব্দটি
    0.39
    스는
    0.38
     타입을
    0.38
     ሁኔታ
    0.38
     আকার
    0.37
    用に
    0.36
    始めて
    0.36
    部分は
    0.35
    "]:
    0.35
    的身
    0.34
    POSITIVE LOGITS
    level
    0.60
    级
    0.59
    कालीन
    0.59
    級
    0.55
     स्तरीय
    0.55
    स्तरीय
    0.54
    -
    0.49
    कालिक
    0.47
    type
    0.47
     कालीन
    0.46
    Act Density 0.148%

    No Known Activations