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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accommodation
    -0.07
     всего
    -0.07
     مؤ
    -0.07
     IsActive
    -0.06
     hc
    -0.06
     pilgrimage
    -0.06
     opportun
    -0.06
    box
    -0.06
     sharp
    -0.06
    	gbc
    -0.06
    POSITIVE LOGITS
    Translation
    0.07
     ECB
    0.06
     появи
    0.06
    UCCESS
    0.06
    気に入
    0.06
    liğe
    0.06
    CLIENT
    0.06
    ERR
    0.06
    _objects
    0.06
     будинку
    0.06
    Act Density 0.027%

    No Known Activations