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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming or data structures

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

    variable assignments or code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vorkommen
    -0.42
    Herzliche
    -0.38
     varsa
    -0.37
     yoksa
    -0.36
     metų
    -0.36
     чтобы
    -0.35
     nedeniyle
    -0.35
    PYX
    -0.34
    iarkan
    -0.34
     prouve
    -0.34
    POSITIVE LOGITS
    IsMutable
    0.68
    ########.
    0.62
    protoimpl
    0.56
    parsedMessage
    0.51
     createState
    0.50
     propOrder
    0.50
    ariConfig
    0.49
    WithIOException
    0.49
    MigrationBuilder
    0.49
     informée
    0.48
    Act Density 0.061%

    No Known Activations