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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <byte
    -0.07
    ずっと
    -0.07
    旎
    -0.07
     rospy
    -0.07
     Rolex
    -0.07
    DirectoryName
    -0.07
     Vlad
    -0.07
    觌
    -0.07
    䴥
    -0.07
     ödeme
    -0.07
    POSITIVE LOGITS
    −
    0.08
     −
    0.08
     />';↵
    0.07
     synthes
    0.07
    Inserted
    0.07
    urred
    0.07
    풍
    0.07
    ollow
    0.07
    荡
    0.06
     Lawyer
    0.06
    Act Density 0.003%

    No Known Activations