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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Leading
    -0.07
    مديرية
    -0.07
     אש
    -0.06
     dependencies
    -0.06
    ब
    -0.06
    מלחמת
    -0.06
    动摇
    -0.06
    igious
    -0.06
    맴
    -0.06
    服务能力
    -0.06
    POSITIVE LOGITS
    _WEB
    0.08
     RAW
    0.08
     SUB
    0.07
    ][:
    0.07
     mailbox
    0.07
    副本
    0.07
    boxing
    0.07
    	raw
    0.07
    CFG
    0.07
    	sock
    0.07
    Act Density 0.009%

    No Known Activations