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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ывая
    -0.07
     amps
    -0.07
     pushes
    -0.06
    Nice
    -0.06
    Pink
    -0.06
     hơn
    -0.06
     же
    -0.06
     adversely
    -0.06
     CI
    -0.06
     abide
    -0.06
    POSITIVE LOGITS
    ￣￣￣￣
    0.08
    }}">{{$
    0.07
    ीए
    0.07
    GenerationStrategy
    0.07
    ButtonModule
    0.07
    .house
    0.07
    /sign
    0.06
    科技有限公司
    0.06
    .inspect
    0.06
    การเล
    0.06
    Act Density 0.069%

    No Known Activations