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

    Neuronpedia

    INDEX
    Explanations

    text from scientific publications and code documentation

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming and software constructs

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arii
    -0.47
    ella
    -0.45
    unat
    -0.44
    ivent
    -0.43
    werb
    -0.43
    ובות
    -0.43
    wad
    -0.42
    pat
    -0.42
    Leod
    -0.42
     do
    -0.42
    POSITIVE LOGITS
     AssemblyProduct
    0.90
    ScopeManager
    0.79
     contextLoads
    0.78
    ContentAsync
    0.73
    StructEnd
    0.73
     createSlice
    0.72
    AccessorTable
    0.71
     للاسماء
    0.71
    argout
    0.70
    ɵɵ
    0.68
    Act Density 5.185%

    No Known Activations