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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structures

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

    code syntax and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    details
    -0.39
     Soon
    -0.37
    meme
    -0.35
     SOON
    -0.34
    leep
    -0.33
    Soon
    -0.33
    hspace
    -0.32
     frond
    -0.32
    soon
    -0.32
    ferrous
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.59
    DeleteBehavior
    0.53
     kasarigan
    0.53
    invokeLater
    0.52
    StoryboardSegue
    0.49
     linkovi
    0.49
    setVerticalGroup
    0.49
     nakalista
    0.48
    ">//
    0.46
     AssemblyTitle
    0.45
    Act Density 0.198%

    No Known Activations