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

    Neuronpedia

    INDEX
    Explanations

    Locations and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MacDonald
    -0.07
     Thumbnail
    -0.07
    نك
    -0.06
    $$$$
    -0.06
     Borough
    -0.06
    뻑
    -0.06
    Counter
    -0.06
     Tonight
    -0.06
    argo
    -0.06
     Tic
    -0.06
    POSITIVE LOGITS
    cem
    0.07
     يوس
    0.07
     często
    0.06
     revived
    0.06
    ità
    0.06
     washed
    0.06
    ᾑ
    0.06
     neural
    0.06
     crusher
    0.06
    .DAO
    0.06
    Act Density 0.272%

    No Known Activations