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

    Neuronpedia

    INDEX
    Explanations

    compliance and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ë
    0.48
     терито
    0.48
     BasicContainer
    0.46
     Blüten
    0.45
     بغیر
    0.45
    湿度
    0.44
     ভালো
    0.44
     исход
    0.44
    ė
    0.44
     ентитету
    0.43
    POSITIVE LOGITS
     automat
    0.48
    -
    0.45
     avons
    0.44
    /
    0.44
     --
    0.43
    Y
    0.42
    J
    0.42
     &
    0.41
     angl
    0.41
     formats
    0.41
    Act Density 0.001%

    No Known Activations