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

    Neuronpedia

    INDEX
    Explanations

    headers and section titles related to programming or technical documentation

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

    code delimiters or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."));
    -0.61
    ."],
    -0.61
    "");
    -0.59
    __);
    -0.59
    */,
    -0.55
     ""],
    -0.55
    ")));
    -0.54
     "));
    -0.53
    .],
    -0.52
    ]];
    -0.52
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.49
     BEGIN
    0.46
    лару
    0.45
    كويكب
    0.45
    ucksack
    0.45
     esternos
    0.44
    óngase
    0.44
     START
    0.43
     ==
    0.43
    knights
    0.43
    Act Density 0.057%

    No Known Activations