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

    Neuronpedia

    INDEX
    Explanations

    torn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	file
    -0.08
    ض
    -0.07
    ipo
    -0.07
    }
    -0.07
     Method
    -0.07
    CurrentUser
    -0.07
    大力发展
    -0.07
    牧
    -0.06
    ュ
    -0.06
    ้
    -0.06
    POSITIVE LOGITS
    行為
    0.08
    诂
    0.08
    讷
    0.07
     konuşma
    0.07
    钥匙
    0.07
    🕞
    0.07
     SwiftUI
    0.07
    箸
    0.07
     רוצים
    0.07
    행위
    0.07
    Act Density 0.005%

    No Known Activations