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

    Neuronpedia

    INDEX
    Explanations

    equations, mathematical symbols, and specific variable names such as theta, psi, and phi

    oai_token-act-pair · gemini-2.0-flash

    non-English or special characters

    np_token-act-pair-logits · gpt-4o-mini

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $\
    -0.81
    ="\
    -0.74
     للمعارف
    -0.70
    {$\
    -0.69
    }{$\
    -0.67
    OGND
    -0.67
     Î
    -0.66
    Î
    -0.65
    RenderAtEndOf
    -0.65
     alpha
    -0.64
    POSITIVE LOGITS
     XNUMX
    0.54
    بوابة
    0.45
     uș
    0.44
    !("{}",
    0.41
     fusca
    0.41
    УДК
    0.40
    GEBURTS
    0.39
    <sup>
    0.39
     = 
    0.38
     [],
    0.37
    Act Density 1.813%

    No Known Activations