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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tačiau
    -0.45
     siente
    -0.44
     magasiner
    -0.44
     ogóle
    -0.43
     utilizza
    -0.40
     aš
    -0.39
     encontraban
    -0.39
    ukses
    -0.39
    kid
    -0.38
    AndroidJUnit
    -0.38
    POSITIVE LOGITS
    expandindo
    0.89
     nahilalakip
    0.82
     ExecuteAsync
    0.77
    LikeLike
    0.69
    newtheorem
    0.68
    Portály
    0.66
    期刊论文
    0.66
     Paglinawan
    0.65
    eleste
    0.65
     onOptions
    0.65
    Act Density 0.193%

    No Known Activations