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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hive
    -0.07
     zusammen
    -0.07
     лекар
    -0.07
    rello
    -0.06
    .do
    -0.06
     odv
    -0.06
     Facial
    -0.06
     neckline
    -0.06
     Prevent
    -0.06
    .syn
    -0.06
    POSITIVE LOGITS
    ={()
    0.07
    “One
    0.06
    /library
    0.06
    ọ
    0.06
     fall
    0.06
     Tillerson
    0.06
     输入
    0.06
     pleas
    0.06
    ('@/
    0.06
    libraries
    0.06
    Act Density 0.001%

    No Known Activations