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

    Neuronpedia

    INDEX
    Explanations

    difficult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denně
    -0.07
    22
    -0.06
    .appendChild
    -0.06
    орів
    -0.06
    เก
    -0.06
    异常
    -0.06
    -0.06
     खड
    -0.06
     inertia
    -0.06
     Wasser
    -0.06
    POSITIVE LOGITS
    氧
    0.07
    راد
    0.07
    “
    0.07
     DEF
    0.07
     моб
    0.06
     behalf
    0.06
    alfa
    0.06
    "F
    0.06
     presente
    0.06
    \DB
    0.06
    Act Density 0.042%

    No Known Activations