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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity and interest in various topics

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

    interest or curiosity

    np_acts-logits-general · gemini-2.0-flash

    deep interest and curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.69
    MENAFN
    -0.66
    endphp
    -0.65
    //
    -0.64
     _:
    -0.60
    usermodel
    -0.59
    Estima
    -0.57
    \{\\
    -0.57
     Cataloging
    -0.56
    <_>
    -0.56
    POSITIVE LOGITS
     enough
    0.82
     banget
    0.70
     جدًا
    0.67
     للغاية
    0.64
     geworden
    0.59
     Partagez
    0.59
     genoeg
    0.58
     assai
    0.56
     Inscrivez
    0.56
    ísimo
    0.55
    Act Density 0.274%

    No Known Activations