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

    Neuronpedia

    INDEX
    Explanations

    what something is called or means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     준비
    0.41
     ऑन
    0.40
    专属
    0.38
     unable
    0.37
    ぶりの
    0.37
     imali
    0.36
    เตรียม
    0.36
     DURING
    0.36
    釐
    0.36
     досто
    0.35
    POSITIVE LOGITS
    جاتا
    0.45
    fraud
    0.42
    θη
    0.40
    诈
    0.39
     दट
    0.39
    >>;
    0.38
     P
    0.37
    RTT
    0.37
    meed
    0.37
    displaystyle
    0.36
    Act Density 0.000%

    No Known Activations