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

    Neuronpedia

    INDEX
    Explanations

    Important considerations for policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acetoxy
    0.92
    currentSprite
    0.89
    Scenes
    0.88
    们
    0.87
     copii
    0.87
     വ്യത്യസ്ത
    0.86
    Longueur
    0.86
    Lähteet
    0.85
     muestra
    0.85
     Tamaño
    0.85
    POSITIVE LOGITS
     practices
    1.80
     policies
    1.78
     standards
    1.73
     principles
    1.70
     initiatives
    1.61
     metrics
    1.61
     measures
    1.61
     capabilities
    1.57
     protocols
    1.55
     goals
    1.53
    Act Density 0.000%

    No Known Activations