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

    Neuronpedia

    INDEX
    Explanations

    groups and representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oración
    0.29
    ্লিকেশন
    0.29
    endereco
    0.29
     Nosotros
    0.28
    ể
    0.28
     arquivo
    0.28
    arquivo
    0.27
     ricco
    0.27
     '|
    0.26
     correctement
    0.26
    POSITIVE LOGITS
     representations
    0.30
     calorimetry
    0.27
     repres
    0.27
    representations
    0.26
    ALES
    0.26
     inventories
    0.25
     STONE
    0.25
     kilometres
    0.25
     Representations
    0.25
     Росії
    0.24
    Act Density 0.000%

    No Known Activations