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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Xia
    -0.06
    ştır
    -0.06
    pected
    -0.06
     Iv
    -0.06
    plitude
    -0.06
     jt
    -0.06
     bx
    -0.06
    cnt
    -0.06
     Tenant
    -0.06
    POSITIVE LOGITS
     уст
    0.07
    .embed
    0.06
     صفحه
    0.06
     craftsmanship
    0.06
    igs
    0.06
    ereg
    0.06
    ائد
    0.06
     ASSIGN
    0.06
    월까지
    0.06
    اخته
    0.06
    Act Density 0.023%

    No Known Activations