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

    Neuronpedia

    INDEX
    Explanations

    variable declarations and type annotations in programming code

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

    variable declaration or annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.57
     betweenstory
    -0.55
     Савезне
    -0.55
     niega
    -0.49
     mourut
    -0.46
     répondit
    -0.45
    ėjimo
    -0.44
    paravant
    -0.43
     sitten
    -0.42
    horizontalLayout
    -0.42
    POSITIVE LOGITS
    var
    0.75
     var
    0.65
     Var
    0.64
     vars
    0.59
    vars
    0.58
     Vars
    0.57
    Var
    0.54
    Vars
    0.53
     vara
    0.52
     VAR
    0.51
    Act Density 0.001%

    No Known Activations