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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to errors and failures in code execution

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

    error or failed message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.60
     pageNumber
    -0.53
     faſt
    -0.53
     ſta
    -0.52
     diſt
    -0.51
     houſe
    -0.50
     viſ
    -0.50
    ollectionView
    -0.49
     pleaſure
    -0.49
     preſent
    -0.49
    POSITIVE LOGITS
     yks
    0.50
    ništ
    0.41
    stretchr
    0.37
     encantó
    0.37
     חיצוניים
    0.35
    freiheit
    0.35
    jidad
    0.34
     Ponce
    0.34
     uitge
    0.34
    ectoria
    0.34
    Act Density 0.026%

    No Known Activations