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

    Neuronpedia

    INDEX
    Explanations

    close, minimum, fundamental, regardless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dr
    0.50
     между
    0.49
    leigh
    0.46
    rock
    0.45
    ನಾಡ
    0.44
     між
    0.44
     海外
    0.44
     morgan
    0.43
    朝
    0.43
    ther
    0.43
    POSITIVE LOGITS
     authentic
    0.46
     autent
    0.44
    认
    0.42
    ژه
    0.41
    Jesse
    0.40
     সন্ত্রাসী
    0.40
    ംഗ്
    0.39
     authenticity
    0.39
    ূলক
    0.38
    authent
    0.38
    Act Density 0.001%

    No Known Activations