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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and structure

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

    foreign words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.34
     Seg
    -0.33
    PhysRev
    -0.32
    Бахар
    -0.32
     Vern
    -0.31
     Kak
    -0.30
    typeorm
    -0.29
    Serv
    -0.28
     Situ
    -0.27
    internalType
    -0.27
    POSITIVE LOGITS
     nonUne
    0.65
    expandindo
    0.64
    niſſe
    0.59
     Offisielt
    0.59
     Kecil
    0.59
     itinéraires
    0.57
     sekal
    0.57
     hroz
    0.56
     umum
    0.56
     geométrico
    0.55
    Act Density 0.115%

    No Known Activations