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

    Neuronpedia

    INDEX
    Explanations

    character traits and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carattere
    0.43
     stupe
    0.43
     charakter
    0.43
    性格
    0.42
     caractères
    0.40
     caracteres
    0.40
     caract
    0.40
     mehndi
    0.39
     unset
    0.39
     ܐ
    0.39
    POSITIVE LOGITS
     Authent
    0.50
     loyal
    0.48
     Harmony
    0.48
     Loy
    0.48
     Loyalty
    0.47
    नि
    0.47
     idealistic
    0.46
     loyalty
    0.46
     spontaneously
    0.45
     Perfection
    0.45
    Act Density 0.018%

    No Known Activations