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

    Neuronpedia

    INDEX
    Explanations

    nested parentheses and mathematical expressions

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

    Code with nested parentheses and math symbols

    np_acts-logits-general · gemini-2.0-flash

    nested parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖚
    -0.69
    ymce
    -0.67
     besar
    -0.64
     отношению
    -0.62
     her
    -0.61
    ểm
    -0.60
     or
    -0.56
    plaatsen
    -0.56
    𝖞
    -0.55
     of
    -0.55
    POSITIVE LOGITS
    (((
    1.31
     intptr
    1.07
    )(((
    1.06
    ((((
    1.02
    =((
    1.01
     ((((
    1.00
    ([[
    1.00
     (((
    0.96
     Monfieur
    0.94
     raiſ
    0.94
    Act Density 0.243%

    No Known Activations