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

    Neuronpedia

    INDEX
    Explanations

    aspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .focus
    -0.07
    (select
    -0.07
    '])↵↵↵
    -0.07
     Delete
    -0.07
    광
    -0.06
    头
    -0.06
    '})↵↵
    -0.06
     đường
    -0.06
    .Replace
    -0.06
     circulated
    -0.06
    POSITIVE LOGITS
    ikh
    0.07
     النس
    0.07
    ina
    0.07
    μένου
    0.06
     aspects
    0.06
    υπ
    0.06
    arge
    0.06
    inds
    0.06
    _optimizer
    0.06
    asser
    0.06
    Act Density 0.001%

    No Known Activations