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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mang
    -0.07
     مركز
    -0.07
     Source
    -0.07
    ung
    -0.06
     Confederate
    -0.06
    atin
    -0.06
     zonder
    -0.06
     porter
    -0.06
     masc
    -0.06
     sắp
    -0.06
    POSITIVE LOGITS
     clears
    0.07
    =config
    0.07
     queue
    0.06
     مرتبط
    0.06
    istle
    0.06
     blessed
    0.06
     sweeps
    0.06
    Updates
    0.06
    inston
    0.06
     functions
    0.06
    Act Density 0.046%

    No Known Activations