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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     после
    -0.07
     güncel
    -0.07
    یر
    -0.06
     contents
    -0.06
    ало
    -0.06
    preferences
    -0.06
    므로
    -0.06
     collect
    -0.06
    为了
    -0.06
     умень
    -0.06
    POSITIVE LOGITS
     Stainless
    0.07
     Strawberry
    0.06
     README
    0.06
     Supern
    0.06
     Záp
    0.06
     Herbert
    0.06
    ainless
    0.06
    	atomic
    0.06
    UTDOWN
    0.06
     Void
    0.06
    Act Density 0.015%

    No Known Activations