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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements and data structures

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

    Code snippets with curly braces and brackets

    np_acts-logits-general · gemini-2.0-flash

    `{}` placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.11
    GEBURTSDATUM
    -0.89
     betweenstory
    -0.79
     المعيارى
    -0.78
    ImageContext
    -0.74
    Tembelea
    -0.73
     queſta
    -0.72
    Autoritní
    -0.71
    jgl
    -0.70
     للمعارف
    -0.70
    POSITIVE LOGITS
     szint
    0.45
     Nacionales
    0.41
     ebenfalls
    0.37
     ardından
    0.35
     again
    0.34
     rayas
    0.34
     dobles
    0.34
     industriales
    0.33
     plegable
    0.33
     similarly
    0.32
    Act Density 0.613%

    No Known Activations