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

    Neuronpedia

    INDEX
    Explanations

    budget, draw, carries, display, his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ятся
    0.90
    յան
    0.79
    мены
    0.78
    ievers
    0.77
     शुरुआ
    0.76
     стены
    0.73
    iversary
    0.73
    рый
    0.72
    ្សែ
    0.72
    ┙
    0.72
    POSITIVE LOGITS
    Cloud
    0.76
    Light
    0.75
    Cool
    0.72
    #
    0.71
    Re
    0.70
    Cont
    0.70
    Condition
    0.69
    tint
    0.68
    顎
    0.68
    Core
    0.67
    Act Density 0.390%

    No Known Activations