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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .af
    -0.08
     supreme
    -0.07
     э
    -0.07
     benches
    -0.07
     Luz
    -0.07
     суд
    -0.07
     complains
    -0.07
    全力
    -0.07
     Penn
    -0.07
     arcade
    -0.06
    POSITIVE LOGITS
    श
    0.07
    𤩽
    0.07
    nofollow
    0.07
     qed
    0.07
    viol
    0.07
    0.07
     discret
    0.07
    残酷
    0.07
     Dimit
    0.06
    ᥣ
    0.06
    Act Density 0.052%

    No Known Activations