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

    Neuronpedia

    INDEX
    Explanations

    <|start|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jogging
    -0.08
    _rec
    -0.08
    的发展
    -0.08
     تناول
    -0.08
    יתוח
    -0.08
     ataque
    -0.08
    _APPEND
    -0.07
    .Use
    -0.07
     ترسره
    -0.07
     المورد
    -0.07
    POSITIVE LOGITS
     arrests
    0.08
     Sé
    0.08
     Spider
    0.08
    _exit
    0.08
     imposs
    0.07
     Goodbye
    0.07
     Serenity
    0.07
     Arrest
    0.07
     bans
    0.07
     outages
    0.07
    Act Density 0.006%

    No Known Activations