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

    Neuronpedia

    INDEX
    Explanations

    intelligence agencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λεκ
    -0.07
    -camera
    -0.07
    ádu
    -0.07
    馆
    -0.06
     договор
    -0.06
     swore
    -0.06
    メント
    -0.06
    ��
    -0.06
    άνει
    -0.06
    CONTENT
    -0.06
    POSITIVE LOGITS
     Brewer
    0.07
     Shares
    0.07
     Aff
    0.06
     prematurely
    0.06
     photographic
    0.06
    -blind
    0.06
    -function
    0.06
     serviceName
    0.06
     Twilight
    0.06
    UILTIN
    0.06
    Act Density 0.131%

    No Known Activations