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

    Neuronpedia

    INDEX
    Explanations

    symbols and expressions used in mathematical notation

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

    mathematical structures with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conten
    -0.48
     esternos
    -0.46
     outlook
    -0.41
     withdrawal
    -0.40
     extension
    -0.39
     defensive
    -0.38
    قایناقلار
    -0.38
     Chines
    -0.38
     salt
    -0.37
     contented
    -0.37
    POSITIVE LOGITS
    istoitu
    0.71
    ➟
    0.66
    AntiForgeryToken
    0.65
    httphttps
    0.65
    )}{
    0.60
    ]}{
    0.59
    )}}{
    0.58
    )}{(
    0.57
     насељу
    0.57
    󠁮
    0.56
    Act Density 0.153%

    No Known Activations