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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax or function calls

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

    end of code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.72
    NameInMap
    -0.69
    RenderAtEndOf
    -0.67
     المعيارى
    -0.64
    rungsseite
    -0.58
     ujednoznacz
    -0.57
     betweenstory
    -0.57
    }{*}{
    -0.55
    transQ
    -0.53
    SBATCH
    -0.52
    POSITIVE LOGITS
    EndInit
    0.50
     Afterward
    0.42
     sienta
    0.39
     grabado
    0.38
    ówczas
    0.38
     Hopefully
    0.38
    horabuena
    0.37
     limpio
    0.37
    __(/*!
    0.37
    引
    0.37
    Act Density 0.130%

    No Known Activations