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

    Neuronpedia

    INDEX
    Explanations

    two choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    1.88
    ۰
    1.55
    shire
    1.54
    quoi
    1.48
    علی
    1.45
    いた
    1.41
    ச்சூழ
    1.41
     Inicio
    1.40
    ck
    1.38
    VER
    1.38
    POSITIVE LOGITS
    thirds
    2.31
    nd
    1.63
     thirds
    1.56
    ਰ
    1.56
    ppled
    1.54
    <0x92>
    1.53
    tone
    1.43
    มอง
    1.41
    हरी
    1.39
    ড্রিম
    1.38
    Act Density 0.580%

    No Known Activations