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

    Neuronpedia

    INDEX
    Explanations

    variables and function definitions in programming code

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

    code change context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.46
    endphp
    -0.45
    SharedDtor
    -0.45
    zzleHttp
    -0.44
     siyang
    -0.43
     BoxDecoration
    -0.42
    Anhalt
    -0.40
    iomanip
    -0.40
     triangulation
    -0.40
    //{
    -0.39
    POSITIVE LOGITS
    verwijspagina
    0.58
     Италијани
    0.54
    farwyddwr
    0.51
    Tikang
    0.44
     otherwise
    0.44
    isy
    0.42
    ❋
    0.41
    otherwise
    0.40
     Otherwise
    0.40
     etc
    0.40
    Act Density 0.020%

    No Known Activations