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

    Neuronpedia

    INDEX
    Explanations

    statements expressing belief or conviction regarding the importance and impact of various concepts

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

    Belief or opinion

    np_acts-logits-general · gemini-2.0-flash

    expressing belief and opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.68
    TagHelpers
    -0.64
    igshid
    -0.61
    <?
    -0.61
     assumed
    -0.58
     imagined
    -0.56
    ("")]
    -0.55
     seemed
    -0.54
     समीक्षक
    -0.53
    XmlAccessorType
    -0.53
    POSITIVE LOGITS
     possano
    0.57
     suitable
    0.55
     aéro
    0.55
     sufficient
    0.55
    suitable
    0.54
     verrez
    0.54
    ganggu
    0.53
     devriez
    0.51
    hassee
    0.50
     muualla
    0.50
    Act Density 0.416%

    No Known Activations