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

    Neuronpedia

    INDEX
    Explanations

    Due

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sebastian
    -0.06
     الی
    -0.06
    ategorical
    -0.06
     глуб
    -0.06
    ями
    -0.06
     �
    -0.06
    arro
    -0.06
    ently
    -0.06
    (chr
    -0.06
    Neo
    -0.06
    POSITIVE LOGITS
     Due
    0.10
     due
    0.10
     reason
    0.08
    due
    0.08
    unexpected
    0.07
     newsletter
    0.07
     Основ
    0.07
    Due
    0.07
    /home
    0.07
    .FALSE
    0.07
    Act Density 0.028%

    No Known Activations