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

    Neuronpedia

    INDEX
    Explanations

    code structures that involve annotations or attributes in programming languages

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

    public, @, class, comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.81
    RTEX
    -0.76
     queſta
    -0.73
     témoig
    -0.68
    principalColumn
    -0.66
     FetchType
    -0.66
    InitVars
    -0.66
     oprot
    -0.66
     unknownFields
    -0.65
    ftagPool
    -0.65
    POSITIVE LOGITS
    public
    0.59
     public
    0.54
    @
    0.45
     @
    0.43
    class
    0.40
     //
    0.38
     class
    0.36
    //
    0.35
    PUBLIC
    0.35
     público
    0.34
    Act Density 0.007%

    No Known Activations