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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ceases
    0.70
    Standing
    0.70
     deixe
    0.68
    battle
    0.67
    stretched
    0.66
     reusing
    0.66
    ceased
    0.65
     withstand
    0.65
     lend
    0.64
     lends
    0.64
    POSITIVE LOGITS
     wide
    0.78
     Wide
    0.68
    ्रेस
    0.60
    мимо
    0.60
     Graf
    0.60
     широ
    0.58
    riter
    0.58
     широкий
    0.58
    Wide
    0.58
    IVEN
    0.57
    Act Density 0.067%

    No Known Activations