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

    Neuronpedia

    INDEX
    Explanations

    control flow statements in code, specifically loops and conditional statements

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

    conditional and loop constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wes
    -0.39
    <eos>
    -0.37
     متحده
    -0.36
    Portály
    -0.36
    homonymie
    -0.35
     cyber
    -0.34
     Ajay
    -0.34
     footwear
    -0.34
     Freder
    -0.34
     aircraft
    -0.34
    POSITIVE LOGITS
    makeConstraints
    0.71
    fjspx
    0.68
    Hochspringen
    0.60
     $_"
    0.60
    AnchorStyles
    0.59
     esfuer
    0.58
    ]")]
    0.58
    ientras
    0.58
    if
    0.57
    WebServlet
    0.56
    Act Density 0.007%

    No Known Activations