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

    Neuronpedia

    INDEX
    Explanations

    commands and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inú
    0.37
     poteva
    0.35
     agak
    0.35
    ږئ
    0.35
     boton
    0.34
    र्दू
    0.34
     automated
    0.34
     leech
    0.34
     gaman
    0.34
     unico
    0.33
    POSITIVE LOGITS
    8
    0.37
    GOOD
    0.35
    입니다
    0.34
    分别
    0.34
    6
    0.34
    4
    0.33
    为
    0.33
    来说
    0.32
    Wrapper
    0.32
    нтов
    0.32
    Act Density 0.005%

    No Known Activations