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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liter
    -0.09
    zę
    -0.08
     eder
    -0.08
     ملك
    -0.07
     време
    -0.07
    �
    -0.07
     executivo
    -0.07
     ambiance
    -0.07
    376
    -0.07
    满
    -0.07
    POSITIVE LOGITS
     cope
    0.09
    快速
    0.09
    安心
    0.09
    쉽
    0.08
     получать
    0.08
     capture
    0.08
     conveniently
    0.08
     добиться
    0.08
    peer
    0.07
     избежать
    0.07
    Act Density 0.089%

    No Known Activations