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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to numbers and values

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

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➟
    -0.39
     vs
    -0.38
    istoitu
    -0.38
    WD
    -0.37
    vs
    -0.37
    +#+#
    -0.37
    BB
    -0.37
    PC
    -0.37
    󠁮
    -0.36
    FC
    -0.35
    POSITIVE LOGITS
     يتيمه
    0.79
     ſeveral
    0.62
     faſt
    0.60
    expandindo
    0.59
     reaſon
    0.58
    entrion
    0.58
    uxxxx
    0.56
     queſta
    0.56
    videobot
    0.55
     ſta
    0.53
    Act Density 0.109%

    No Known Activations