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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values associated with parameters or measurements

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

    Numbers followed by units

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h4>
    -0.63
    initializeApp
    -0.55
     الاطلاع
    -0.55
    ↵
    -0.53
    Charsets
    -0.53
    ---*/
    -0.53
    </th>
    -0.53
     (?,
    -0.52
    <tbody>
    -0.51
    璨
    -0.50
    POSITIVE LOGITS
    ㅡ
    0.79
    ㅜ
    0.71
    ㅣ
    0.69
    RetentionPolicy
    0.67
     Eſ
    0.63
    ㅗ
    0.61
     pleaſure
    0.60
    ㅔ
    0.59
     myſelf
    0.59
    FilterChain
    0.59
    Act Density 0.155%

    No Known Activations