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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zz
    -0.07
    allocator
    -0.06
    fk
    -0.06
     Bitmap
    -0.06
    zf
    -0.06
    cing
    -0.06
     One
    -0.06
    แก
    -0.06
    ,↵↵
    -0.06
    .acc
    -0.06
    POSITIVE LOGITS
     eman
    0.07
     Afterwards
    0.07
    aternion
    0.07
     негатив
    0.07
     करव
    0.07
     Rwanda
    0.06
    Random
    0.06
    imonial
    0.06
    (Application
    0.06
    ーバ
    0.06
    Act Density 0.040%

    No Known Activations