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

    Neuronpedia

    INDEX
    Explanations

    AI followed by disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поэтому
    0.48
    ა
    0.48
    ي
    0.47
    ޟ
    0.47
    𝚊
    0.47
    ্টের
    0.46
    ༦
    0.46
    ጶ
    0.45
    ുകളെ
    0.45
    <unused1049>
    0.45
    POSITIVE LOGITS
    ning
    0.57
    ren
    0.56
    ier
    0.52
     in
    0.50
    man
    0.49
     it
    0.45
    ile
    0.43
    ifying
    0.43
    rad
    0.42
    1
    0.42
    Act Density 0.051%

    No Known Activations