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

    Neuronpedia

    INDEX
    Explanations

    programming language statements that include system or library references

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

    Code-related imports, usings, or namespaces

    np_acts-logits-general · gemini-2.0-flash

    programming standard libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.76
    httphttps
    -0.70
    verwijspagina
    -0.69
     <=",
    -0.69
    ніципалі
    -0.66
     ModelRenderer
    -0.66
    pecabe
    -0.65
    䊱
    -0.65
     Photocase
    -0.63
     дописавши
    -0.63
    POSITIVE LOGITS
    stdc
    0.50
    complexContent
    0.40
    iostream
    0.39
     date
    0.38
    stdio
    0.36
     dates
    0.34
    stdlib
    0.34
    console
    0.33
    cstdlib
    0.31
    try
    0.30
    Act Density 0.003%

    No Known Activations