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

    Neuronpedia

    INDEX
    Explanations

    Code and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gro
    -0.28
    aver
    -0.27
    rawn
    -0.27
    åĩĨç¡®æĢ§
    -0.27
     allegedly
    -0.25
     save
    -0.25
     reckon
    -0.25
    å®īåħ¨æĦŁ
    -0.23
     manifest
    -0.23
    omm
    -0.23
    POSITIVE LOGITS
    vol
    0.32
    客
    0.27
    ä¸Ģé¦ĸ
    0.24
    odian
    0.24
    {:
    0.24
    vy
    0.24
    çī¹çĤ¹æĺ¯
    0.24
     makeStyles
    0.24
    çĽĹ
    0.23
    çİĩè¾¾åĪ°
    0.23
    Act Density 0.013%

    No Known Activations