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

    Neuronpedia

    INDEX
    Explanations

    VA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mehmet
    -0.07
    clidean
    -0.06
     bewild
    -0.06
     جزء
    -0.06
    命令
    -0.06
    .depend
    -0.06
     beads
    -0.06
    みたい
    -0.06
    保持
    -0.06
     impeccable
    -0.06
    POSITIVE LOGITS
     VA
    0.14
     va
    0.09
    VA
    0.09
     verse
    0.08
    .exc
    0.08
     verses
    0.08
     Va
    0.07
     doubt
    0.07
    -го
    0.07
     court
    0.07
    Act Density 0.001%

    No Known Activations