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

    Neuronpedia

    INDEX
    Explanations

    personality types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     graduellement
    0.40
     elevators
    0.39
     namen
    0.38
    enregistrement
    0.38
    randomNumber
    0.38
    軗
    0.38
     enemigos
    0.38
     дове
    0.37
     geomet
    0.37
     estánd
    0.36
    POSITIVE LOGITS
     personality
    0.82
     fictional
    0.78
     character
    0.75
     شخصیت
    0.75
    personality
    0.68
    性格
    0.68
    Personality
    0.68
     Personality
    0.64
    Character
    0.64
     traits
    0.64
    Act Density 0.002%

    No Known Activations