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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tight
    -0.07
    μαν
    -0.06
     candid
    -0.06
     audits
    -0.06
     control
    -0.06
     ambitions
    -0.06
     Speak
    -0.06
    IRTH
    -0.06
     myocard
    -0.06
     crop
    -0.06
    POSITIVE LOGITS
    ويت
    0.07
     puis
    0.07
    nie
    0.07
    ifs
    0.07
    .Files
    0.06
    ��
    0.06
     Už
    0.06
    후기
    0.06
    ınız
    0.06
    --,
    0.06
    Act Density 0.555%

    No Known Activations