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

    Neuronpedia

    INDEX
    Explanations

    number and quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     progrès
    0.46
     prawd
    0.43
     Penis
    0.43
     minerales
    0.42
     Humidity
    0.41
     abilit
    0.41
     méth
    0.41
     évaluation
    0.41
     demandas
    0.41
     précieux
    0.40
    POSITIVE LOGITS
    centric
    0.46
    四
    0.46
    north
    0.44
     اړه
    0.44
    groups
    0.43
    straat
    0.43
     கூட்டு
    0.43
    remarks
    0.43
     России
    0.43
     రెండు
    0.43
    Act Density 0.001%

    No Known Activations