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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¹´åĨħ
    -0.27
    è¾Ļ
    -0.26
     ETA
    -0.26
    æ¯ı人
    -0.26
     Correction
    -0.26
     cost
    -0.25
    bows
    -0.25
    wä
    -0.25
    å¹´çļĦ
    -0.25
     Cost
    -0.25
    POSITIVE LOGITS
    ()._
    0.28
    ãģ¡ãĤĩãģĨãģ©
    0.27
    侵害
    0.27
    uisse
    0.26
     fran
    0.26
     Derby
    0.26
     entails
    0.25
     toxic
    0.24
    autop
    0.24
     thrown
    0.24
    Act Density 0.348%

    No Known Activations