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

    Neuronpedia

    INDEX
    Explanations

    Catching up word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Procedures
    -0.10
     procedures
    -0.08
     Traditionally
    -0.08
     bağlı
    -0.08
     предусматри
    -0.08
    ատ
    -0.08
     өң
    -0.08
    -bordered
    -0.08
     multilingual
    -0.07
     Procedure
    -0.07
    POSITIVE LOGITS
     overt
    0.10
    Tracking
    0.10
     parab
    0.09
    Debt
    0.09
     tracking
    0.09
     tracked
    0.09
     पीछ
    0.09
     eventual
    0.09
    Relative
    0.09
     chasing
    0.08
    Act Density 0.032%

    No Known Activations