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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to product features and specifications

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

    Follows a punctuation mark or other symbol

    np_acts-logits-general · gemini-2.0-flash

    punctuation and symbols before questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.67
    IsContent
    -0.65
     للمعارف
    -0.60
    endencies
    -0.60
    ureusement
    -0.59
    Dislikes
    -0.59
     समीक्षाओं
    -0.58
    amodel
    -0.58
     halen
    -0.57
    ACKNOWLEDGEMENTS
    -0.56
    POSITIVE LOGITS
     very
    0.63
     high
    0.60
     Adopted
    0.56
    Adopted
    0.54
     adopted
    0.53
     suitable
    0.53
     easy
    0.52
    high
    0.52
     exquisite
    0.51
     lightweight
    0.51
    Act Density 0.050%

    No Known Activations