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

    Neuronpedia

    INDEX
    Explanations

    accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Directed
    -0.07
    auc
    -0.06
    dup
    -0.06
    隠
    -0.06
     Plaint
    -0.06
     Comparative
    -0.06
     RV
    -0.06
     mest
    -0.06
     sanitary
    -0.06
    _uart
    -0.06
    POSITIVE LOGITS
    -par
    0.06
    ційного
    0.06
    :name
    0.06
    uffer
    0.06
    limitations
    0.06
    _-
    0.06
     guilty
    0.06
    .sources
    0.06
     Його
    0.06
    %</
    0.06
    Act Density 0.036%

    No Known Activations