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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    581
    -0.06
    .Memory
    -0.06
    705
    -0.06
    誌
    -0.06
     Cooler
    -0.06
    Maintenance
    -0.06
    vang
    -0.06
     Fond
    -0.06
     thiếu
    -0.06
    736
    -0.06
    POSITIVE LOGITS
     introduced
    0.07
     والن
    0.06
     gettimeofday
    0.06
     nama
    0.06
     rol
    0.06
     trà
    0.06
     designing
    0.06
    τις
    0.06
    UPLE
    0.06
    音楽
    0.06
    Act Density 0.138%

    No Known Activations