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

    Neuronpedia

    INDEX
    Explanations

    terms related to legality and regulatory actions

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

    followed by prepositions or related terms

    np_acts-logits-general · gemini-2.0-flash

    diagnosis of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -1.19
     '\\;'
    -1.18
    tagHelperRunner
    -1.18
    -1.15
     tartalomajánló
    -1.14
    mybatisplus
    -1.13
    MigrationBuilder
    -1.13
    styleType
    -1.11
    expandindo
    -1.11
     Italijanski
    -1.09
    POSITIVE LOGITS
    …
    0.91
    ↵
    0.81
    <eos>
    0.80
     …
    0.79
    ↵↵
    0.76
    ……
    0.75
    ….
    0.75
    </h2>
    0.73
    .
    0.69
    The
    0.68
    Act Density 1.122%

    No Known Activations