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

    Neuronpedia

    INDEX
    Explanations

    diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Speak
    -0.07
     như
    -0.07
     Choosing
    -0.07
     Кан
    -0.06
     unfair
    -0.06
     flu
    -0.06
     hosp
    -0.06
     Castillo
    -0.06
     ✓
    -0.06
     döndü
    -0.06
    POSITIVE LOGITS
    로는
    0.07
     dbContext
    0.07
     уд
    0.06
     Parties
    0.06
     -->↵↵
    0.06
     November
    0.06
    Widget
    0.06
     FILES
    0.06
    елі
    0.06
     ملت
    0.06
    Act Density 0.013%

    No Known Activations