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

    Neuronpedia

    INDEX
    Explanations

    code syntax related to functions and their parameters

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

    directional light type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.75
    parsedMessage
    -0.72
     $_(
    -0.71
     nakalista
    -0.71
     $_"
    -0.71
     zwiſchen
    -0.69
    Fordítás
    -0.66
     ujednoznacz
    -0.66
     ſta
    -0.65
     ſeine
    -0.65
    POSITIVE LOGITS
    IntoConstraints
    0.40
     준
    0.33
     Neither
    0.31
     Ready
    0.31
     ready
    0.31
    set
    0.30
     Before
    0.29
     set
    0.28
     rendent
    0.28
    Neither
    0.28
    Act Density 0.017%

    No Known Activations