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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addTarget
    -0.06
     swarm
    -0.06
    installed
    -0.06
     yarn
    -0.06
     연결
    -0.06
     involves
    -0.06
     distur
    -0.06
     backgroundImage
    -0.06
     в
    -0.05
     embarked
    -0.05
    POSITIVE LOGITS
    elli
    0.07
     steroid
    0.07
    .Buttons
    0.07
    �
    0.06
     подс
    0.06
    OPTION
    0.06
    147
    0.06
     rapide
    0.06
     втор
    0.06
     Regiment
    0.06
    Act Density 0.008%

    No Known Activations