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

    Neuronpedia

    INDEX
    Explanations

    greater than or increase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    0.87
     intellig
    0.79
    :>
    0.79
    ►
    0.77
     Boltzmann
    0.77
    靂
    0.73
     bastard
    0.72
     >,
    0.72
     تور
    0.72
    unordered
    0.72
    POSITIVE LOGITS
    若
    1.19
     possibile
    1.09
     необхід
    1.08
    疋
    1.04
    无法
    1.03
    受益
    1.02
     потрі
    1.00
     若
    1.00
    此之外
    0.99
    這裡
    0.98
    Act Density 0.000%

    No Known Activations