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

    Neuronpedia

    INDEX
    Explanations

    references to direct control variables in research studies, particularly in relation to demographics and measurements

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

    colon, dash, or parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.90
    [@BOS@]
    -0.88
    <unused41>
    -0.88
    <unused79>
    -0.88
    <unused28>
    -0.88
    <unused14>
    -0.88
    <unused68>
    -0.87
    <unused74>
    -0.87
    <unused23>
    -0.87
    <unused8>
    -0.87
    POSITIVE LOGITS
    :
    0.49
    ,
    0.42
     :
    0.37
     =
    0.33
     —
    0.31
    /
    0.30
    ：
    0.28
    E
    0.28
    B
    0.28
    ()
    0.28
    Act Density 0.104%

    No Known Activations