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

    Neuronpedia

    INDEX
    Explanations

    respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ball
    0.55
    ുകൊണ്ട
    0.52
    U
    0.52
    3
    0.50
    ball
    0.50
    ipl
    0.50
    Sh
    0.50
     little
    0.50
    Lord
    0.50
     gloomy
    0.49
    POSITIVE LOGITS
    それぞれ
    1.12
     respectively
    1.10
     respectivement
    1.08
    分别
    1.01
     jeweils
    1.00
    分别是
    0.99
     respectivamente
    0.96
     それぞれ
    0.93
    respectively
    0.92
     masing
    0.89
    Act Density 0.023%

    No Known Activations