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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    慎
    -0.07
    (include
    -0.06
    命
    -0.06
    ۰۰۰
    -0.06
     Ideally
    -0.06
    無し�
    -0.06
    fahren
    -0.06
    format
    -0.06
     tro
    -0.06
     deaths
    -0.06
    POSITIVE LOGITS
     понима
    0.07
     aujourd
    0.07
     stiff
    0.06
    ra
    0.06
     Regina
    0.06
    아
    0.06
    こんにちは
    0.06
     Reader
    0.06
    ('@/
    0.06
    .RegisterType
    0.06
    Act Density 0.018%

    No Known Activations