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

    Neuronpedia

    INDEX
    Explanations

    references to research authors and their affiliations

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

    East Asian surnames

    np_acts-logits-general · gemini-2.0-flash

    surnames followed by initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.74
     transfieras
    -0.62
     CURLOPT
    -0.58
    didSet
    -0.57
    phant
    -0.54
     بيها
    -0.53
    ModelBuilder
    -0.53
    rlpool
    -0.52
     ThemeData
    -0.52
    multicolumn
    -0.51
    POSITIVE LOGITS
     Y
    0.78
     X
    0.63
     YC
    0.54
     SY
    0.53
    +#+#
    0.53
     YS
    0.51
     YB
    0.51
    Y
    0.50
     entanto
    0.49
    løs
    0.49
    Act Density 0.211%

    No Known Activations