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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving equations

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

    Fractions or expressions with fraction-like syntax

    np_acts-logits-general · gemini-2.0-flash

    latex fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `
    -0.83
    rungsseite
    -0.81
    bootstrapcdn
    -0.78
    </b>
    -0.76
    /*
    -0.73
    IsContent
    -0.73
    </i>
    -0.73
     متعلقه
    -0.69
     \[
    -0.67
    \]
    -0.66
    POSITIVE LOGITS
    <strong>
    1.84
    CPtr
    0.58
     --;
    0.54
    ástica
    0.53
     **/
    0.52
    frac
    0.51
     aback
    0.51
    RegressionTest
    0.49
    **/
    0.48
    InstanceState
    0.47
    Act Density 0.049%

    No Known Activations