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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρό
    -0.07
    �
    -0.07
     Gors
    -0.07
     firmly
    -0.07
     Thou
    -0.06
     मज
    -0.06
     Kot
    -0.06
    utron
    -0.06
    ôn
    -0.06
     mutual
    -0.06
    POSITIVE LOGITS
    "",↵
    0.06
    acionales
    0.06
    $page
    0.06
    implode
    0.06
     ｜
    0.06
    >());↵
    0.06
     dieser
    0.06
    ValidateAntiForgeryToken
    0.06
    аб
    0.06
    ่ใช
    0.06
    Act Density 0.000%

    No Known Activations