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

    Neuronpedia

    INDEX
    Explanations

    backslashes used in LaTeX commands

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

    for usepackage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.51
    RotationOrder
    -0.47
    transQ
    -0.47
    ckså
    -0.47
     ſch
    -0.45
     houſe
    -0.45
    inSlope
    -0.44
     itſelf
    -0.44
    astéroïdes
    -0.43
     deſt
    -0.43
    POSITIVE LOGITS
    saraba
    0.56
    '])->
    0.55
     \
    0.54
    $_['
    0.50
    ophylla
    0.48
    })}\
    0.48
    ))\
    0.47
    }}}\
    0.45
     Mey
    0.45
     paper
    0.45
    Act Density 0.033%

    No Known Activations