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

    Neuronpedia

    INDEX
    Explanations

    XML schema definitions and namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.74
     miscon
    1.55
    汴
    1.55
    랜드
    1.53
    त
    1.53
    是为了
    1.52
     Jasmine
    1.47
    ו
    1.46
    样子
    1.44
     svog
    1.42
    POSITIVE LOGITS
    DX
    1.71
    Proto
    1.67
    taine
    1.64
    raut
    1.61
     상관
    1.59
    ző
    1.55
    kale
    1.55
     pă
    1.52
     Besonders
    1.52
    k
    1.52
    Act Density 0.000%

    No Known Activations