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

    Neuronpedia

    INDEX
    Explanations

    references to formal documentation and letters of support

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

    Acknowledgements, introductions, or endorsements

    np_acts-logits-general · gemini-2.0-flash

    endorsement, certificate, letter, or introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.45
    WebElementEntity
    -0.41
    </thead>
    -0.38
    Guil
    -0.36
     estekak
    -0.36
    Reporter
    -0.36
    TokenNameDOT
    -0.36
    mors
    -0.35
    bille
    -0.35
    ➌
    -0.35
    POSITIVE LOGITS
     endorsement
    0.66
     certificate
    0.62
    Endor
    0.60
     endorsements
    0.60
     Endor
    0.59
     testimonial
    0.56
     endorsed
    0.55
     endorse
    0.55
     certification
    0.54
     testimonials
    0.53
    Act Density 0.273%

    No Known Activations