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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbolic representations in dense text

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

    LaTeX expressions

    np_acts-logits-general · gemini-2.0-flash

    special characters in math mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.76
     armado
    -0.72
     mxArray
    -0.72
     orde
    -0.70
    \}\
    -0.70
     kohdetta
    -0.69
    }')
    -0.68
    manta
    -0.68
     Erden
    -0.67
     Marta
    -0.66
    POSITIVE LOGITS
    ^{
    1.15
     ^{
    0.91
    )^{
    0.86
    .^
    0.82
    $^{
    0.80
    @^
    0.76
    ))^{
    0.76
    })^{
    0.76
    躇
    0.75
    }}^{
    0.74
    Act Density 0.675%

    No Known Activations