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

    Neuronpedia

    INDEX
    Explanations

    structured mathematical expressions and formatting commands

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

    LaTeX environments: array, split, aligned

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новниш
    -0.47
     @"/
    -0.43
    WithMany
    -0.40
    Rhestr
    -0.39
     arşivlendi
    -0.38
    webElementXpaths
    -0.35
    ngOn
    -0.34
    principalColumn
    -0.34
    addCriterion
    -0.34
     Italijani
    -0.34
    POSITIVE LOGITS
    endcsname
    0.60
    fromnode
    0.58
    setVerticalGroup
    0.57
    <unused8>
    0.54
    <unused43>
    0.54
    [@BOS@]
    0.54
    <unused14>
    0.54
    <unused52>
    0.54
    <unused41>
    0.54
    <unused51>
    0.54
    Act Density 0.587%

    No Known Activations