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

    Neuronpedia

    INDEX
    Explanations

    software component names and technical terms related to programming

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

    Lists with enumerated items

    np_acts-logits-general · gemini-2.0-flash

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.64
     par
    -0.50
     ban
    -0.47
    ियाँ
    -0.46
     ,
    -0.46
     Mit
    -0.46
     mit
    -0.45
    |$.
    -0.45
     …
    -0.45
     send
    -0.45
    POSITIVE LOGITS
    enumi
    0.84
    évaluateur
    0.83
    setcounter
    0.82
    abestanden
    0.80
     Sodom
    0.79
    AddTagHelper
    0.78
     Esau
    0.78
    Rhestr
    0.77
    TagMode
    0.77
    GEBURTS
    0.76
    Act Density 0.005%

    No Known Activations