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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     двиг
    -0.07
     aluminum
    -0.07
     mitigation
    -0.07
    licative
    -0.06
    Manage
    -0.06
     ğ
    -0.06
     omn
    -0.06
     kra
    -0.06
     medida
    -0.06
    "$
    -0.06
    POSITIVE LOGITS
     progressed
    0.08
     pik
    0.06
    姓名
    0.06
     unacceptable
    0.06
    朋友
    0.06
    ictions
    0.06
    graphql
    0.06
     cần
    0.06
     ventured
    0.06
    .shtml
    0.06
    Act Density 0.002%

    No Known Activations