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

    Neuronpedia

    INDEX
    Explanations

    values and their corresponding attributes in a structured format

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

    Comes after "value" in HTML-like structures

    np_acts-logits-general · gemini-2.0-flash

    expect(...).toBe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -0.49
    1
    -0.49
     Bucure
    -0.47
     consectetur
    -0.46
     The
    -0.44
    2
    -0.44
    </u>
    -0.43
     supérieures
    -0.41
    !
    -0.41
     Schmitz
    -0.41
    POSITIVE LOGITS
    <td>
    1.26
    CloseOperation
    1.04
     surla
    0.89
     snippetHide
    0.85
     GenerationType
    0.85
    مصادر
    0.85
     שוליים
    0.84
    0.83
     الحره
    0.81
    ագրություններ
    0.79
    Act Density 0.003%

    No Known Activations