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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text or math surrounded by '$' symbols

    np_acts-logits-general · gemini-2.0-flash

    background transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    teden
    -0.52
    ScopeManager
    -0.52
    goku
    -0.48
    Бахар
    -0.47
    mögens
    -0.46
    TagHelpers
    -0.46
    MultipartFile
    -0.46
     Exposition
    -0.46
    виси
    -0.45
    sopp
    -0.45
    POSITIVE LOGITS
     rotation
    0.74
     transformations
    0.74
     rotations
    0.73
     rotate
    0.73
     invariance
    0.73
    RotationOrder
    0.70
     Rotation
    0.68
     rotates
    0.68
    :✨
    0.68
    таратура
    0.67
    Act Density 1.111%

    No Known Activations