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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements commonly used in code or data formatting

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

    set specifiers like {a, b, c}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transpa
    -0.41
    "");
    -0.36
    <tbody>
    -0.36
    Secret
    -0.35
    Ferdinand
    -0.35
     Perd
    -0.35
    Baud
    -0.35
    secre
    -0.34
    SECRET
    -0.34
     Secret
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.75
    ChildScrollView
    0.56
    ngths
    0.52
     <<<<<<<<<<<<<<
    0.50
    rungsseite
    0.49
     pinulongan
    0.45
     numerus
    0.45
     beginnetje
    0.45
    帖最后由
    0.44
    nezeu
    0.44
    Act Density 0.322%

    No Known Activations