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

    Neuronpedia

    INDEX
    Explanations

    crear, utilizar, give

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˆ‚
    0.54
     ,"
    0.48
     visok
    0.46
    丂
    0.46
    ótes
    0.45
    नाइटेड
    0.44
     ót
    0.44
    িন
    0.43
     citadel
    0.43
     artigos
    0.42
    POSITIVE LOGITS
     in
    0.44
     versus
    0.44
    ressive
    0.44
     incluir
    0.43
     vs
    0.43
     commencer
    0.43
    မီ
    0.42
     up
    0.42
    一开始
    0.42
     begin
    0.42
    Act Density 0.014%

    No Known Activations