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

    Neuronpedia

    INDEX
    Explanations

    to followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     новые
    0.80
     eficiência
    0.75
     efic
    0.72
     atualizar
    0.72
     stabilization
    0.72
     necessárias
    0.70
     realignment
    0.70
     operacional
    0.68
     efficiency
    0.68
     smoothing
    0.68
    POSITIVE LOGITS
    拥有
    0.70
     ધરા
    0.70
    擁有
    0.64
    具备
    0.64
    具有
    0.63
    0
    0.60
    δο
    0.58
     Iceland
    0.58
     have
    0.57
     possessing
    0.56
    Act Density 0.075%

    No Known Activations