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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tours
    -0.07
     cycle
    -0.07
     tour
    -0.07
    _connection
    -0.07
    θούν
    -0.06
    asan
    -0.06
     paramet
    -0.06
     corpses
    -0.06
     poetic
    -0.06
    formula
    -0.06
    POSITIVE LOGITS
     İslam
    0.07
     надання
    0.06
    //
↵
↵
    0.06
    准备
    0.06
     ”↵↵
    0.06
    lasyon
    0.06
     çalışma
    0.06
    ONGLONG
    0.06
    .AddScoped
    0.06
    //↵↵↵
    0.06
    Act Density 0.001%

    No Known Activations