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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edward
    -0.06
    	K
    -0.06
    Rew
    -0.06
     Matter
    -0.06
     Faction
    -0.06
    _FACTOR
    -0.06
    程序
    -0.06
    ��
    -0.06
    аторы
    -0.06
    ाग
    -0.06
    POSITIVE LOGITS
    .DialogResult
    0.09
     masih
    0.08
    ‌ده
    0.07
     době
    0.07
     прост
    0.07
    /bg
    0.07
     Labrador
    0.07
     crunchy
    0.07
    *dt
    0.07
     بوده
    0.06
    Act Density 0.374%

    No Known Activations