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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buluş
    -0.06
    OfBirth
    -0.06
    itizer
    -0.06
    人类
    -0.06
    ากาศ
    -0.06
    iod
    -0.06
     هذا
    -0.05
     Rif
    -0.05
     informed
    -0.05
     Rath
    -0.05
    POSITIVE LOGITS
     acclaim
    0.10
     embr
    0.07
     applause
    0.07
    building
    0.07
    ERM
    0.07
     Hiện
    0.07
    _BYTE
    0.07
     polling
    0.07
     Burger
    0.07
     corp
    0.06
    Act Density 0.009%

    No Known Activations