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

    Neuronpedia

    INDEX
    Explanations

    various professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enviar
    0.38
     pourront
    0.37
     puissent
    0.36
     eux
    0.36
     mogą
    0.35
     могат
    0.33
     doivent
    0.33
     mohou
    0.33
     possam
    0.33
    それぞれ
    0.32
    POSITIVE LOGITS
     an
    0.44
     a
    0.43
     in
    0.41
     является
    0.38
    gen
    0.38
    ga
    0.36
     Arts
    0.35
     vowel
    0.34
     admirably
    0.34
     activism
    0.34
    Act Density 0.009%

    No Known Activations