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

    Neuronpedia

    INDEX
    Explanations

    references to file paths or URLs

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

    code comments parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.47
     imp
    -0.38
    intios
    -0.34
     e
    -0.31
    Sucesor
    -0.30
     localObject
    -0.29
    P
    -0.29
     event
    -0.29
     I
    -0.29
    invokeLater
    -0.29
    POSITIVE LOGITS
     AssemblyTitle
    0.64
    iastes
    0.63
     IBOutlet
    0.63
     好文分享
    0.61
    <unused41>
    0.61
    <unused17>
    0.61
    <unused1>
    0.60
    <unused3>
    0.60
    [@BOS@]
    0.60
    <pad>
    0.60
    Act Density 0.001%

    No Known Activations