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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     postData
    -0.07
     قنا
    -0.07
    宜宾
    -0.07
    闽
    -0.07
     dish
    -0.07
     House
    -0.07
    משקיע
    -0.06
     Essential
    -0.06
     очень
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
     BindingFlags
    0.07
     zamówienia
    0.07
     bufio
    0.07
     الشمال
    0.07
    lararas
    0.07
    יזם
    0.07
    冻结
    0.07
     periodo
    0.07
    ⟦
    0.07
    outines
    0.06
    Act Density 0.002%

    No Known Activations