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

    Neuronpedia

    INDEX
    Explanations

    character traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automated
    0.49
     spawning
    0.48
     datasets
    0.46
     automation
    0.46
     automating
    0.43
    automated
    0.43
     increases
    0.43
     اڈ
    0.43
     bytecode
    0.42
     automate
    0.41
    POSITIVE LOGITS
     personality
    1.19
     Personality
    1.07
    Personality
    1.07
     personalidade
    1.02
    personality
    1.02
    性格
    0.99
     personalità
    0.97
     charisma
    0.96
     personalidad
    0.93
     temperament
    0.91
    Act Density 0.059%

    No Known Activations