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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publication metrics or data

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

    Citations with DOI identifiers

    np_acts-logits-general · gemini-2.0-flash

    ſind, itſelf, myſelf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     r
    -0.68
     R
    -0.66
     
    -0.58
     tri
    -0.57
     qu
    -0.57
     G
    -0.57
     c
    -0.56
     Qu
    -0.56
     '
    -0.55
     F
    -0.55
    POSITIVE LOGITS
     ―――――
    1.26
     ſind
    1.08
     itſelf
    1.08
     myſelf
    1.07
     stiefel
    1.04
     Efq
    1.04
     faſt
    1.03
     ་་
    1.01
     Eſ
    1.01
     cdti
    1.00
    Act Density 0.922%

    No Known Activations