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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facebook
    -0.07
     Vector
    -0.07
     Tran
    -0.06
     temporada
    -0.06
    .bed
    -0.06
     Manuel
    -0.06
     annotation
    -0.06
     electrónico
    -0.06
     Constant
    -0.06
     anime
    -0.06
    POSITIVE LOGITS
    煙
    0.06
     yêu
    0.06
    çuk
    0.06
     ontvangst
    0.06
    amik
    0.06
    霞
    0.06
    ci
    0.06
     طبي
    0.06
     bậc
    0.06
    新增
    0.06
    Act Density 0.000%

    No Known Activations