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

    Neuronpedia

    INDEX
    Explanations

    Thinking, perception, realization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poster
    -0.08
    ocker
    -0.07
    .ActionBar
    -0.07
    庵
    -0.07
    aturdays
    -0.07
    .help
    -0.06
     Attendance
    -0.06
    اقة
    -0.06
    ignty
    -0.06
    أسم
    -0.06
    POSITIVE LOGITS
    FL
    0.07
     TAS
    0.07
     dua
    0.07
    meta
    0.06
    🚅
    0.06
    妥
    0.06
     na
    0.06
     accuracy
    0.06
    NUM
    0.06
    ).
    0.06
    Act Density 0.059%

    No Known Activations