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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variable syntax in programming code

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

    {$ variables with code"}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NavigationView
    -0.50
    渡
    -0.44
     tranſ
    -0.40
     Ferdin
    -0.40
     ark
    -0.38
     arxiv
    -0.38
     pág
    -0.38
     anal
    -0.38
     ſee
    -0.37
     exerci
    -0.37
    POSITIVE LOGITS
    {$
    1.68
     {$
    1.58
    ){$
    0.90
    {$\
    0.81
     {$\
    0.80
    }{$
    0.80
     {{$
    0.75
    {'
    0.69
    ">{{$
    0.68
     ***!
    0.65
    Act Density 0.010%

    No Known Activations