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

    Neuronpedia

    INDEX
    Explanations

    contrasting or conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igham
    0.42
     தனிநாயகம்
    0.42
    Prince
    0.41
    រួម
    0.41
    ampler
    0.41
     লইয়
    0.41
     ব্যয়ে
    0.40
    气氛
    0.40
     শ্বশুর
    0.40
     Christensen
    0.39
    POSITIVE LOGITS
     process
    0.46
    行動
    0.45
    ல்
    0.45
     পুরো
    0.44
    자동차
    0.43
    c
    0.43
    アイ
    0.43
    ទ្ធ
    0.43
     excellence
    0.42
    مین
    0.42
    Act Density 0.004%

    No Known Activations