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

    Neuronpedia

    INDEX
    Explanations

    permissive AI chatbot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     विजय
    -0.10
     réuss
    -0.08
     सफलता
    -0.08
    ktime
    -0.08
     victory
    -0.07
     both
    -0.07
    .install
    -0.07
     magnifique
    -0.07
     victoire
    -0.07
    .notifications
    -0.07
    POSITIVE LOGITS
    িনী
    0.09
    Vs
    0.09
     restricciones
    0.09
    .Restr
    0.08
    Faq
    0.08
     oblig
    0.08
     قادر
    0.08
     speziellen
    0.08
    ابر
    0.08
    দন্ত
    0.08
    Act Density 0.009%

    No Known Activations