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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شخصية
    -0.07
    Workbook
    -0.06
    ยวก
    -0.06
    MH
    -0.06
    lüğü
    -0.06
    irie
    -0.06
    .PackageManager
    -0.06
     Mathematic
    -0.06
     lawy
    -0.06
    bh
    -0.06
    POSITIVE LOGITS
     boredom
    0.07
     탈
    0.06
     místní
    0.06
    nant
    0.06
     dominated
    0.06
    컨
    0.06
     senses
    0.06
     انگلیسی
    0.06
    Reuse
    0.06
     cmp
    0.05
    Act Density 0.025%

    No Known Activations