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

    Neuronpedia

    INDEX
    Explanations

    takes courage and integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enthusiasm
    0.88
     enthusiastic
    0.80
     enthusi
    0.77
     enthous
    0.73
     entusiasmo
    0.71
     उत्सा
    0.71
     entusi
    0.71
     Enthusi
    0.70
     ambitious
    0.68
     friendly
    0.67
    POSITIVE LOGITS
    Character
    1.00
     character
    0.97
     integrity
    0.96
     Character
    0.94
    character
    0.93
    integrity
    0.88
     karakter
    0.88
     Integrity
    0.86
     integridad
    0.83
     Charakter
    0.77
    Act Density 0.028%

    No Known Activations