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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pied
    -0.06
     TOKEN
    -0.06
     ＼
    -0.06
    _compile
    -0.06
    иля
    -0.06
    _helpers
    -0.06
    ,the
    -0.06
     intrusive
    -0.06
     робити
    -0.06
    ,:,:
    -0.06
    POSITIVE LOGITS
     дит
    0.07
     реб
    0.07
     knows
    0.07
     realize
    0.06
     Recon
    0.06
    тю
    0.06
    ihan
    0.06
     　　 　
    0.06
     applying
    0.06
    sendMessage
    0.06
    Act Density 0.068%

    No Known Activations