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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fadeIn
    -0.06
    ICC
    -0.06
     conversation
    -0.06
     deduction
    -0.06
     Patrick
    -0.06
    เหมาะ
    -0.06
     reconciliation
    -0.06
    umont
    -0.06
     ultimately
    -0.06
     forgiven
    -0.06
    POSITIVE LOGITS
     CDDL
    0.07
     rež
    0.06
     Rusya
    0.06
    creat
    0.06
     çeşitli
    0.06
     startX
    0.06
    ('//*[@
    0.06
    นวย
    0.06
     wishlist
    0.06
    ').
    0.06
    Act Density 0.002%

    No Known Activations