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

    Neuronpedia

    INDEX
    Explanations

    LaTeX mathematical formatting commands

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.44
    ########.
    -0.38
    ↵
    -0.36
    L
    -0.34
    P
    -0.33
     województwie
    -0.32
    ↵↵
    -0.30
    forName
    -0.29
    $_['
    -0.29
     seng
    -0.29
    POSITIVE LOGITS
    itemize
    0.89
    ſelben
    0.82
     للاسماء
    0.76
    ConstraintMaker
    0.73
    UnusedPrivate
    0.71
    WriteTagHelper
    0.70
    enumii
    0.69
     müſſen
    0.68
    httphttps
    0.66
    <unused8>
    0.65
    Act Density 0.007%

    No Known Activations