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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دود
    -0.07
    جيل
    -0.07
     Canary
    -0.07
    索
    -0.06
    _cont
    -0.06
     '.';↵
    -0.06
     circulated
    -0.06
    執
    -0.06
     '_',
    -0.06
    _billing
    -0.06
    POSITIVE LOGITS
     He
    0.07
     Pok
    0.07
     Sa
    0.07
     Koh
    0.06
     They
    0.06
     We
    0.06
     shin
    0.06
    indsay
    0.06
     Lov
    0.06
     Sim
    0.06
    Act Density 0.001%

    No Known Activations