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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biç
    -0.07
    Administrator
    -0.06
     frank
    -0.06
     Scar
    -0.06
     عمومی
    -0.06
    Scar
    -0.06
     Frid
    -0.06
     Indianapolis
    -0.06
       
↵
    -0.06
    (BASE
    -0.06
    POSITIVE LOGITS
    少年
    0.07
    ("%.
    0.06
    цать
    0.06
     worthless
    0.06
     KUR
    0.06
     standout
    0.06
    otionEvent
    0.06
    yük
    0.06
     wealth
    0.06
     yrs
    0.06
    Act Density 0.000%

    No Known Activations