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

    Neuronpedia

    INDEX
    Explanations

    variable declarations and assignments in programming code

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

    variable declarations and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blum
    -0.32
    Wild
    -0.32
     and
    -0.32
     Wandel
    -0.30
     veilig
    -0.30
     пода
    -0.29
    true
    -0.29
     musim
    -0.29
    Safe
    -0.29
     cambiado
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.84
     MainAxisSize
    0.80
    errHandler
    0.78
    ChildScrollView
    0.73
    <unused23>
    0.69
    <pad>
    0.69
    <unused28>
    0.69
    SequentialGroup
    0.69
    <unused8>
    0.69
    [@BOS@]
    0.69
    Act Density 0.020%

    No Known Activations