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

    Neuronpedia

    INDEX
    Explanations

    improvements and increases in confidence or understanding

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

    improved confidence and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schwab
    -0.41
     Seif
    -0.41
    ors
    -0.40
     wciąż
    -0.39
     autor
    -0.38
     mesto
    -0.38
    лтамалар
    -0.38
     pił
    -0.38
     Flüs
    -0.38
    Lat
    -0.37
    POSITIVE LOGITS
    UserScript
    0.64
    ftagPool
    0.59
    ScopeManager
    0.52
     bezeichneter
    0.52
    interopRequire
    0.51
    RTEE
    0.50
    PreInfinity
    0.46
    ngdoc
    0.45
    modelBuilder
    0.45
    ArgsConstructor
    0.44
    Act Density 0.163%

    No Known Activations