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

    Neuronpedia

    INDEX
    Explanations

    medium or moderate levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     punishments
    0.81
     সংকো
    0.77
     constricted
    0.75
     constrained
    0.75
     milestones
    0.75
     inaction
    0.73
     centralized
    0.73
     burdened
    0.73
     impoverished
    0.73
     limitations
    0.72
    POSITIVE LOGITS
    Medium
    2.45
     Medium
    2.42
     medium
    2.10
    medium
    2.07
     MEDIUM
    1.86
    MEDIUM
    1.70
     mediums
    1.60
     मीडियम
    1.59
    Moderate
    1.33
     Moderate
    1.31
    Act Density 0.266%

    No Known Activations