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

    Neuronpedia

    INDEX
    Explanations

    吗

    np_max-act · gemini-2.0-flash

    phrases that inquire about assistance or support.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ant
    -0.06
    ultiply
    -0.06
    boys
    -0.06
    bot
    -0.06
    -upload
    -0.06
    "}}>↵
    -0.06
    یان
    -0.06
    ANS
    -0.06
    tics
    -0.06
    .ind
    -0.06
    POSITIVE LOGITS
    吗
    0.07
     bh
    0.07
     dùng
    0.07
     metab
    0.06
     ncols
    0.06
     resembles
    0.06
    kah
    0.06
     hasta
    0.06
     haystack
    0.06
     kappa
    0.06
    Act Density 0.004%

    No Known Activations