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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical symbols for equations and formulas

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

    bracketed labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ByVersion
    -0.57
    Autoritní
    -0.55
    Rujuakan
    -0.50
    بوابة
    -0.49
     Marín
    -0.47
    SEGUIR
    -0.47
    onDestroy
    -0.46
     enfans
    -0.46
     Administrativna
    -0.46
    PreferredItem
    -0.46
    POSITIVE LOGITS
    \[
    2.13
     \[
    1.29
    \[\
    1.07
    httphttps
    0.73
     <<<<<<<<<<<<<<
    0.72
    \[
    0.71
    KommentareTeilen
    0.70
     \\[
    0.69
    \\[
    0.66
    %\[
    0.66
    Act Density 0.119%

    No Known Activations