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

    Neuronpedia

    INDEX
    Explanations

    Author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advisory
    -0.06
     Karel
    -0.06
     semaphore
    -0.06
     morality
    -0.06
     پل
    -0.06
     север
    -0.06
     past
    -0.06
     butterfly
    -0.06
    .network
    -0.06
    زيد
    -0.06
    POSITIVE LOGITS
    318
    0.07
    poke
    0.07
    时
    0.06
     Glide
    0.06
     INCIDENTAL
    0.06
    <!--
    0.06
    forced
    0.06
     Brill
    0.06
    crear
    0.06
    „D
    0.06
    Act Density 0.004%

    No Known Activations