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

    Neuronpedia

    INDEX
    Explanations

    degradable materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Що
    -0.07
     Pokémon
    -0.07
    Finite
    -0.07
    ____
    -0.07
    vice
    -0.07
    Crear
    -0.06
    ocols
    -0.06
    ينا
    -0.06
     Peoples
    -0.06
    огда
    -0.06
    POSITIVE LOGITS
    671
    0.07
     đỏ
    0.06
    	Output
    0.06
     uygulam
    0.06
     dbContext
    0.06
    ermalink
    0.06
     نموده
    0.06
     založ
    0.06
     веществ
    0.06
    FILENAME
    0.06
    Act Density 0.004%

    No Known Activations