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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in code or text

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trui
    -0.40
     AssemblyProduct
    -0.38
    +#+
    -0.37
     оригіналу
    -0.37
    GRect
    -0.35
    DockStyle
    -0.35
    rolling
    -0.34
    atschappij
    -0.34
    </tfoot>
    -0.34
    chemise
    -0.34
    POSITIVE LOGITS
    featureID
    0.64
    parsedMessage
    0.64
    Autoritní
    0.54
    SBATCH
    0.52
     zijne
    0.48
    elemField
    0.47
    principalColumn
    0.47
     singkat
    0.47
     children
    0.46
    dafx
    0.46
    Act Density 0.000%

    No Known Activations