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

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to user interface components and data handling

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

    Code related terms

    np_acts-logits-general · gemini-2.0-flash

    code structure and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )";
    -1.58
    )”.
    -1.52
    ."]
    -1.51
    .”)
    -1.49
    .";
    -1.45
    ).”
    -1.45
    .'”
    -1.43
    ’.”
    -1.40
    .")
    -1.39
    )».
    -1.36
    POSITIVE LOGITS
     here
    0.95
     -
    0.93
     part
    0.82
     for
    0.81
     --
    0.77
    ...
    0.76
    ----------------
    0.76
     stuff
    0.74
     (
    0.74
    .
    0.72
    Act Density 0.306%

    No Known Activations