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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and indicators of specificity in various contexts

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

    musikstykker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.47
     AssemblyProduct
    -0.47
    HasForeignKey
    -0.45
    WritableDatabase
    -0.39
     विश्वसनीयता
    -0.38
    ftagPool
    -0.38
     ホイール
    -0.37
    we
    -0.37
     Bürgermeister
    -0.36
     Spitze
    -0.36
    POSITIVE LOGITS
     queſta
    0.55
     transfieras
    0.53
    BibitemShut
    0.50
    Reyn
    0.48
     geſch
    0.47
    niſſe
    0.47
     estekak
    0.47
    ніципалі
    0.47
     zuſammen
    0.46
    bibfield
    0.46
    Act Density 0.025%

    No Known Activations