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

    Neuronpedia

    INDEX
    Explanations

    Travel itineraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Кар
    -0.09
     cheating
    -0.07
     Attribute
    -0.07
     Float
    -0.07
     Зд
    -0.07
     birds
    -0.06
     monitoring
    -0.06
     Travis
    -0.06
     chalk
    -0.06
    Ending
    -0.06
    POSITIVE LOGITS
    怎么
    0.06
    aption
    0.06
     обесп
    0.06
    696
    0.06
    abilir
    0.06
    /drivers
    0.05
     }
↵
↵
↵
↵
    0.05
    .demo
    0.05
     Syrians
    0.05
    ُّ
    0.05
    Act Density 0.015%

    No Known Activations