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

    Neuronpedia

    INDEX
    Explanations

    work, role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     תמ
    -0.08
     interf
    -0.08
    נג
    -0.06
    组图
    -0.06
    安东
    -0.06
    コミュニケ
    -0.06
     Zend
    -0.06
     vriend
    -0.06
    消费品
    -0.06
     sost
    -0.06
    POSITIVE LOGITS
     bulk
    0.08
    req
    0.07
    ,e
    0.06
    ){↵
    0.06
    ENCY
    0.06
    /U
    0.06
     pies
    0.06
     ""),↵
    0.06
    明显的
    0.06
     routinely
    0.06
    Act Density 0.160%

    No Known Activations