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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ισ
    0.50
     Zusätzlich
    0.48
    𒋀
    0.48
     дея
    0.46
     pią
    0.45
    ⟋
    0.44
    冋
    0.44
     μετα
    0.43
    ]，
    0.43
     同时
    0.43
    POSITIVE LOGITS
     solitaire
    0.49
     uncertainty
    0.48
     two
    0.47
     shopping
    0.47
    :
    0.47
    によって
    0.47
    two
    0.46
    altz
    0.46
    ucket
    0.46
     laisser
    0.46
    Act Density 0.004%

    No Known Activations