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

    Neuronpedia

    INDEX
    Explanations

    elements related to ease of use and user-friendliness in tasks or processes

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

    easy / simpler things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.44
    protoimpl
    -0.41
    writeFieldEnd
    -0.38
     MainAxisSize
    -0.37
     disambiguazione
    -0.37
     nowo
    -0.35
    tableFuture
    -0.33
     peł
    -0.32
     naso
    -0.32
    تقاوى
    -0.31
    POSITIVE LOGITS
     easy
    1.47
    easy
    1.44
    Easy
    1.42
     Easy
    1.41
     EASY
    1.25
     ease
    1.19
    EASY
    1.16
     easier
    1.15
     Ease
    1.14
    easier
    1.13
    Act Density 0.101%

    No Known Activations