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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and special characters representing complex concepts

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

    Mathematical or programmatic expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.88
     ​
    -0.84
    Glej
    -0.68
     �
    -0.65
    writeFieldEnd
    -0.65
     
    -0.64
     Мексичка
    -0.64
     %)
    -0.63
    InitVars
    -0.63
     يتيمه
    -0.62
    POSITIVE LOGITS
    (\
    0.79
    =\
    0.70
    [\
    0.69
    -\
    0.68
    +\
    0.67
    $,
    0.65
    >\
    0.64
    \{
    0.62
    .\
    0.61
    $\\
    0.59
    Act Density 0.624%

    No Known Activations