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

    Neuronpedia

    INDEX
    Explanations

    OTHERWISE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bru
    -0.08
     denote
    -0.07
    رش
    -0.07
    磁
    -0.07
     dashed
    -0.07
    ክ
    -0.07
     Corm
    -0.06
     perpendicular
    -0.06
    един
    -0.06
     Krank
    -0.06
    POSITIVE LOGITS
    格網站
    0.07
    进军
    0.07
    產業
    0.07
    뵉
    0.07
     jewellery
    0.07
    ﻸ
    0.07
    |;↵
    0.07
     позволит
    0.07
    ecided
    0.07
    帷
    0.07
    Act Density 0.000%

    No Known Activations