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

    Neuronpedia

    INDEX
    Explanations

    -century

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逃
    -0.07
    .pipe
    -0.07
    .Tr
    -0.07
     bleeding
    -0.07
    (reverse
    -0.07
     نخ
    -0.07
     Ergebn
    -0.06
     softer
    -0.06
     safer
    -0.06
    =request
    -0.06
    POSITIVE LOGITS
    -century
    0.08
     Medieval
    0.07
    距離
    0.07
     roofing
    0.06
    IN
    0.06
    áf
    0.06
     Victorian
    0.06
     University
    0.06
     <-
    0.06
    VIN
    0.06
    Act Density 0.004%

    No Known Activations