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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stole
    -0.07
     Babe
    -0.07
    に入って
    -0.07
    междуна
    -0.07
     просто
    -0.07
     מספיק
    -0.07
     weren
    -0.06
    汽
    -0.06
     وب
    -0.06
     앞으로
    -0.06
    POSITIVE LOGITS
    市教育
    0.07
    variants
    0.07
    creation
    0.07
    筹资
    0.07
    破裂
    0.07
    ControlEvents
    0.07
    UIView
    0.07
    可疑
    0.07
    孳
    0.07
    פרי
    0.07
    Act Density 0.000%

    No Known Activations