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

    Neuronpedia

    INDEX
    Explanations

    URLs and forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monroe
    -0.07
     Manny
    -0.07
    .ASCII
    -0.07
    kim
    -0.07
    女子
    -0.07
    穿着
    -0.07
    ZR
    -0.07
    .Batch
    -0.07
    	RTLU
    -0.06
    工作人员
    -0.06
    POSITIVE LOGITS
    做大
    0.07
     dominant
    0.07
    _converter
    0.07
     Fallon
    0.07
    .compute
    0.06
     משמעותי
    0.06
     remarkable
    0.06
    _checksum
    0.06
     placer
    0.06
     granularity
    0.06
    Act Density 0.021%

    No Known Activations