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

    Neuronpedia

    INDEX
    Explanations

    underscore characters used in code or programming syntax

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

    elements of code and their syntactical structures

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

    code and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recent
    -0.56
     
    -0.50
     http
    -0.46
    ,
    -0.45
     inter
    -0.45
     no
    -0.44
     |
    -0.44
     become
    -0.44
     da
    -0.43
     grand
    -0.42
    POSITIVE LOGITS
     pinulongan
    1.09
     myſelf
    1.09
     itſelf
    0.98
     فريبيس
    0.97
    ftagPool
    0.93
     Monfieur
    0.90
     Jefus
    0.89
    CompilerServices
    0.89
     مرئيه
    0.88
    ſelves
    0.87
    Act Density 0.007%

    No Known Activations