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

    Neuronpedia

    INDEX
    Explanations

    targeted marketing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oeff
    -0.07
     acomp
    -0.07
    uese
    -0.06
     annoying
    -0.06
    urface
    -0.06
    かけ
    -0.06
     consum
    -0.06
    會
    -0.06
     bigot
    -0.06
     perm
    -0.06
    POSITIVE LOGITS
    ư
    0.07
    登录
    0.07
     knives
    0.06
    lius
    0.06
     erotik
    0.06
    ("/",
    0.06
     witness
    0.06
    _bridge
    0.06
    <Document
    0.06
    -auth
    0.06
    Act Density 0.023%

    No Known Activations