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

    Neuronpedia

    INDEX
    Explanations

    code blocks and their structures

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

    public modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndProject
    -0.90
     queſta
    -0.79
    uxxxx
    -0.78
    IntoConstraints
    -0.77
     betweenstory
    -0.77
     autorytatywna
    -0.72
    oredCriteria
    -0.69
    Diwedd
    -0.69
     AssemblyProduct
    -0.64
     незавершена
    -0.64
    POSITIVE LOGITS
    public
    0.58
     public
    0.52
    Public
    0.45
    @
    0.44
    ↵
    0.41
    ↵↵
    0.40
    private
    0.38
     Public
    0.37
     público
    0.36
     @
    0.35
    Act Density 0.002%

    No Known Activations