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

    Neuronpedia

    INDEX
    Explanations

    technical programming constructs and methods

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

    `Click here` or `id(` or `r =`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.87
     Administrativna
    -0.86
    GEBURTSDATUM
    -0.77
    parsedMessage
    -0.77
     queſta
    -0.73
    httphttps
    -0.73
     surla
    -0.72
     purpoſe
    -0.72
     otomatig
    -0.69
     ſtate
    -0.68
    POSITIVE LOGITS
     all
    0.49
     each
    0.47
     
    0.47
     some
    0.42
     tuturor
    0.42
     for
    0.42
     these
    0.42
     in
    0.41
    char
    0.41
     re
    0.40
    Act Density 0.147%

    No Known Activations