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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance and efficiency

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

    followed by "as" indicating comparison

    np_acts-logits-general · gemini-2.0-flash

    adjective as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}},
    -0.65
    <?>>
    -0.63
    __(/*!
    -0.63
    enterOuterAlt
    -0.62
    Архівовано
    -0.61
     ?></
    -0.59
    ?></
    -0.57
     }},
    -0.55
    assero
    -0.54
    CreateMap
    -0.53
    POSITIVE LOGITS
     quanto
    1.01
     wie
    0.74
     للاسماء
    0.73
     mogelijk
    0.72
     as
    0.62
     assim
    0.62
     ό
    0.61
     possible
    0.58
    aarrggbb
    0.55
     kuin
    0.53
    Act Density 0.116%

    No Known Activations