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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or symbols used in formal expressions

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marcher
    -0.31
     crédit
    -0.31
    Sorted
    -0.31
    RotationOrder
    -0.30
     growing
    -0.30
     sicheren
    -0.29
     pembunuhan
    -0.29
    采
    -0.29
     relationship
    -0.29
     discriminación
    -0.29
    POSITIVE LOGITS
     שוליים
    0.74
    Архівовано
    0.59
     MainAxisSize
    0.57
     iconLine
    0.57
    겜
    0.54
    BASEPATH
    0.54
    DotNetBar
    0.53
    DockStyle
    0.53
    argout
    0.53
    UnusedPrivate
    0.52
    Act Density 0.000%

    No Known Activations