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

    Neuronpedia

    INDEX
    Explanations

    special characters and specific structured elements in the text

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

    parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.84
     $_(
    -0.79
    ſicht
    -0.78
    iſche
    -0.77
     zwiſchen
    -0.76
    <unused74>
    -0.75
     erſt
    -0.75
    <unused68>
    -0.75
    [@BOS@]
    -0.75
    <unused14>
    -0.75
    POSITIVE LOGITS
    <eos>
    0.38
    </tr>
    0.35
    </table>
    0.33
     נוסף
    0.33
    }());
    0.32
     Hope
    0.30
    CreateModel
    0.30
    ↵↵
    0.28
    .
    0.28
    None
    0.27
    Act Density 0.004%

    No Known Activations