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

    Neuronpedia

    INDEX
    Explanations

    percentage to decimal conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    э
    0.61
     sweetened
    0.58
     desired
    0.56
     favorable
    0.56
     quench
    0.55
    ที่
    0.53
     melted
    0.53
     deems
    0.53
    ே
    0.53
     minimized
    0.52
    POSITIVE LOGITS
     Geschäfts
    0.73
     Harriet
    0.71
     Pharmacology
    0.70
     professora
    0.69
     enseignants
    0.69
     Haunted
    0.68
     chercheurs
    0.68
     Hazards
    0.67
     recherches
    0.67
    chairs
    0.67
    Act Density 0.010%

    No Known Activations