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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腕
    -0.07
    制品
    -0.07
          ↵      ↵
    -0.07
     Sz
    -0.06
    -fl
    -0.06
     pant
    -0.06
     فإ
    -0.06
     GST
    -0.06
    账号
    -0.06
    .z
    -0.06
    POSITIVE LOGITS
     Spaces
    0.07
     milf
    0.07
    ILING
    0.07
     squad
    0.07
    .Concurrent
    0.07
    .Usage
    0.07
    	strcat
    0.07
    ,SLOT
    0.07
    חס
    0.07
     minced
    0.07
    Act Density 0.009%

    No Known Activations