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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĿĵ
    -0.27
    iel
    -0.27
    iales
    -0.26
    ä½łæĺ¯
    -0.26
    æĺ¯åIJ¦åŃĺåľ¨
    -0.26
     Bul
    -0.25
    iert
    -0.25
    semblies
    -0.25
    _EXISTS
    -0.25
    kiye
    -0.24
    POSITIVE LOGITS
    çĹĺ
    0.26
     Pandora
    0.26
     Coat
    0.26
    ç§Ģ
    0.26
     warranties
    0.25
    åıĸ
    0.25
    çĸ½
    0.25
     Hass
    0.25
    æīĢèĥ½
    0.24
    rend
    0.24
    Act Density 2.600%

    No Known Activations