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

    Neuronpedia

    INDEX
    Explanations

    possessive pronoun followed by positive trait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hältnis
    0.44
     Uses
    0.44
     రహ
    0.42
    Uses
    0.41
    omorph
    0.40
     durations
    0.40
    ากาศ
    0.39
     situações
    0.39
     Describes
    0.39
     अवसर
    0.38
    POSITIVE LOGITS
     expertise
    1.16
     ingenuity
    1.03
     creativity
    1.01
    expertise
    0.92
     enthusiasm
    0.90
     talents
    0.88
     professionalism
    0.86
     Expertise
    0.84
     diligence
    0.80
     creatividad
    0.80
    Act Density 0.006%

    No Known Activations