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

    Neuronpedia

    INDEX
    Explanations

    character archetypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äume
    0.60
    ጆች
    0.59
     tejidos
    0.58
    ஓம்
    0.57
    िलास
    0.56
     Exponential
    0.56
     primaryStage
    0.56
    婚姻
    0.55
     prezzi
    0.55
     componentWill
    0.55
    POSITIVE LOGITS
     villain
    1.03
     robot
    1.02
     cyborg
    1.02
     cowboy
    0.97
     characters
    0.96
     robots
    0.96
     misfit
    0.94
     villains
    0.94
     rogue
    0.93
     guy
    0.92
    Act Density 0.693%

    No Known Activations