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

    Neuronpedia

    INDEX
    Explanations

    instances of structured data or code-like syntax within the text

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

    Code snippets with special characters

    np_acts-logits-general · gemini-2.0-flash

    code boundaries and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षाएं
    -0.63
     EClass
    -0.61
    بوابة
    -0.56
     Kem
    -0.53
    cillary
    -0.50
    റ്റ
    -0.49
     &___
    -0.48
    Kem
    -0.48
    की
    -0.47
     sopr
    -0.47
    POSITIVE LOGITS
    */)
    0.67
    +:+
    0.65
    */;
    0.63
     nakalista
    0.58
    migrationBuilder
    0.58
    ")));
    0.58
    TextHelper
    0.56
    $")
    0.56
     hinaus
    0.56
    》.
    0.55
    Act Density 0.589%

    No Known Activations