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

    Neuronpedia

    INDEX
    Explanations

    individuals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    privileged
    -0.06
    only
    -0.06
     fooled
    -0.06
    _learn
    -0.06
    .White
    -0.06
     Ree
    -0.06
     concealed
    -0.06
    -feed
    -0.06
    Alan
    -0.06
    RW
    -0.06
    POSITIVE LOGITS
    マ
    0.07
    ,
    0.07
     cultiv
    0.06
     فرد
    0.06
    GetWidth
    0.06
     پنج
    0.06
     entity
    0.06
    ">',↵
    0.06
    처럼
    0.06
     Roll
    0.06
    Act Density 0.022%

    No Known Activations