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

    Neuronpedia

    INDEX
    Explanations

    Early stages Managed Services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    恋愛
    0.44
    <0x96>
    0.41
     安心
    0.40
    Viol
    0.37
    {~
    0.37
     नाग
    0.37
    lyrics
    0.37
    量を
    0.34
    容
    0.34
     начин
    0.34
    POSITIVE LOGITS
     TC
    0.41
     Kuch
    0.40
    ermos
    0.40
     રૂપિયા
    0.38
     tc
    0.38
     টাকার
    0.38
    \|$.
    0.38
    ধবার
    0.37
    ResourceManager
    0.37
    LEXPORT
    0.37
    Act Density 0.000%

    No Known Activations