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

    Neuronpedia

    INDEX
    Explanations

    higher rate, significantly higher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    柽
    0.73
    ఫో
    0.70
     पदक
    0.66
    illés
    0.66
    टावा
    0.66
    လိ
    0.65
     Aged
    0.65
    eburger
    0.65
    etel
    0.65
     primaryStage
    0.64
    POSITIVE LOGITS
    <unused2154>
    0.86
     rate
    0.73
    increasing
    0.71
    遠
    0.71
    Rate
    0.69
     higher
    0.69
    far
    0.68
     far
    0.67
     so
    0.67
     vastly
    0.66
    Act Density 0.000%

    No Known Activations