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

    Neuronpedia

    INDEX
    Explanations

    problem 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পন্থ
    0.41
     কৌশল
    0.40
    th
    0.38
    L
    0.38
    N
    0.38
     যাতে
    0.37
    C
    0.37
    と思っています
    0.37
     Bend
    0.37
     Botanic
    0.37
    POSITIVE LOGITS
    ොර
    0.44
    VENTORY
    0.44
    чити
    0.43
    kje
    0.43
    adım
    0.42
    Iniciar
    0.42
    чили
    0.42
     njihov
    0.42
    ברו
    0.42
    ニチイ
    0.42
    Act Density 0.019%

    No Known Activations